{ "fetched_at": "2026-10-19T08:33:43Z", "source_url": "https://www.kaggle.com/competitions/dishcovery-vlm-mtf-cvpr-2025/data", "pages": [ { "name": "data-description", "content": "We provide two splits of challenge data:\n- Training data.\n- Test data.\n\n# Suggested Training Data\n\nTraining data generated by [Precision at Scale framework](https://arxiv.org/abs/2407.03463) is available on HuggingFace 🤗 [here](https://huggingface.co/collections/jesusmolrdv/cvprw-mtf-2025-vlm-challenge-data-67e3b1cd766b4836df868a1b) with two splits:\n- Web split.\n- Synthetic split.\n\n## MTF 2025 VLM Challenge Dataset - Web Split\n\n### Overview\n\nThis dataset is part of the training data for the **CVPR Workshop Metafood 2025 (MTF 2025) VLM Challenge**. It consists of image-text pairs where the images are sourced from the web.\n\nThe dataset has been carefully curated using the **Precision-at-Scale** method, ensuring high relevance and quality for domain-specific tasks.\n\n**Associated Hugging Face Repository:** `jesusmolrdv/MTF25-VLM-Challenge-Dataset-Web`\n\n### Dataset Description\n\n* **Source:** Web-scraped images.\n* **Format:** The dataset hosted on Hugging Face contains a table (similar to a Pandas DataFrame) with two columns:\n * `url`: The URL of the original food image.\n * `caption`: A textual description associated with the image.\n* **Curation:** The selection of image-text pairs was performed using the methodology described in the \"Precision at Scale\" paper (see Citation section).\n\n### How to Use / Download\n\nSince this dataset split contains URLs to images rather than the images themselves, you need to download the images using a tool like [`img2dataset`](https://github.com/rom1504/img2dataset/).\n\n1. **Install dependencies:**\n ```bash\n pip install img2dataset datasets pyarrow pandas\n ```\n\n2. **Prepare the URL list:**\n First, download the dataset metadata (which contains the URLs and captions) from Hugging Face and save it as a local file (e.g., Parquet format). Run this short Python script:\n\n ```python\n from datasets import load_dataset\n import os\n\n hf_dataset_name = \"jesusmolrdv/MTF25-VLM-Challenge-Dataset-Web\"\n metadata_output_file = \"mtf2025_web_metadata.parquet\" # Output file for img2dataset\n\n print(f\"Loading dataset metadata: {hf_dataset_name}\")\n # Ensure you load the correct split, default is often 'train'\n dataset = load_dataset(hf_dataset_name, split=\"train\")\n\n print(f\"Saving metadata to {metadata_output_file}...\")\n # Save in Parquet format, which img2dataset can read efficiently\n dataset.to_parquet(metadata_output_file)\n\n print(\"Metadata file saved successfully.\")\n\n ```\n This script will create a file named `mtf2025_web_metadata.parquet` in the directory where you run it. This file contains the `url` and `caption` columns needed by `img2dataset`.\n\n3. **Download images using `img2dataset` CLI:**\n Now, use the `img2dataset` command in your terminal. Adjust parameters like `output_folder`, `image_size`, and `processes_count` as needed.\n\n ```bash\n img2dataset \\\n --url_list mtf2025_web_metadata.parquet \\\n --input_format \"parquet\" \\\n --url_col \"url\" \\\n --caption_col \"caption\" \\\n --output_format webdataset \\\n --output_folder ./mtf2025_web_images \\\n --processes_count 16 \\\n --thread_count 64 \\\n --image_size 512 \\\n --resize_mode keep_ratio \\\n --save_additional_columns '[\"caption\"]' \\\n --enable_wandb False\n ```\n\n> *Note: Downloading large datasets can take significant time and bandwidth. Some URLs might become inactive over time.*\n\n### Citation\n\nIf you use this dataset in your research or challenge participation, please cite the following paper describing the curation method:\n\n```\n@misc{rodríguezdevera2024precisionscaledomainspecificdatasets,\n title={Precision at Scale: Domain-Specific Datasets On-Demand},\n author={Jesús M Rodríguez-de-Vera and Imanol G Estepa and Ignacio Sarasúa and Bhalaji Nagarajan and Petia Radeva},\n year={2024},\n eprint={2407.03463},\n archivePrefix={arXiv},\n primaryClass={cs.CV},\n url={https://arxiv.org/abs/2407.03463},\n}\n```\n\n## MTF 2025 VLM Challenge Dataset - Synthetic Split\n\n### Overview\n\nThis dataset is part of the training data for the **CVPR Workshop Metafood 2025 (MTF 2025) VLM Challenge**. It consists of image-text pairs where the images are synthetically generated using **[Stable Diffusion 2.1](https://huggingface.co/stabilityai/stable-diffusion-2-1)**.\n\nThe dataset has been carefully curated using the **Precision-at-Scale** method, ensuring high relevance and quality for domain-specific tasks.\n\n**Associated Hugging Face Repository:** `jesusmolrdv/MTF25-VLM-Challenge-Dataset-Synth`\n\n### Dataset Description\n\n* **Source:** Synthetic images generated via Stable Diffusion v2.1.\n* **Format:** The dataset hosted on Hugging Face contains a table (similar to a Pandas DataFrame or Hugging Face `Dataset` object) with two columns:\n * `image`: The PIL (Python Imaging Library) image object itself.\n * `caption`: The textual description (prompt) used to generate the image.\n* **Curation:** The selection/generation process was guided by the methodology described in the \"Precision at Scale\" paper (see Citation section).\n\n### How to Use / Download\n\nThis dataset can be directly loaded using the Hugging Face `datasets` library. The images are embedded within the dataset structure.\n\n1. **Install Hugging Face `datasets` library:**\n ```bash\n pip install datasets Pillow\n ```\n\n2. **Load the dataset using Python:**\n\n ```python\n from datasets import load_dataset\n \n # Load the dataset from Hugging Face\n hf_dataset_name = \"jesusmolrdv/MTF25-VLM-Challenge-Dataset-Synth\"\n print(f\"Loading dataset: {hf_dataset_name}...\")\n \n # Load the desired split (e.g., 'train')\n # Use streaming=True for large datasets to avoid downloading everything at once\n # dataset = load_dataset(hf_dataset_name, split=\"train\", streaming=True)\n dataset = load_dataset(hf_dataset_name, split=\"train\") # Loads the entire split into memory/cache\n \n print(\"Dataset loaded successfully.\")\n \n # Accessing data (example for non-streaming)\n if dataset:\n print(f\"Number of examples in split: {len(dataset)}\")\n # Get the first example\n first_example = dataset[0]\n img = first_example['image']\n caption = first_example['caption']\n \n print(\"\\nFirst example:\")\n print(f\" Caption: {caption}\")\n print(f\" Image type: {type(img)}\")\n print(f\" Image mode: {img.mode}\")\n print(f\" Image size: {img.size}\")\n \n # You can display the image (requires matplotlib or other library)\n # import matplotlib.pyplot as plt\n # plt.imshow(img)\n # plt.title(caption)\n # plt.axis('off')\n # plt.show()\n \n # Iterate through the dataset (example)\n # print(\"\\nIterating through first 5 examples:\")\n # for i, example in enumerate(dataset):\n # if i >= 5:\n # break\n # print(f\" Example {i+1}: Caption - {example['caption'][:50]}...\") # Print first 50 chars of caption\n # Process example['image'] and example['caption'] as needed\n else:\n print(\"Failed to load dataset.\")\n \n # Example of iterating with streaming=True\n # print(\"\\nIterating through first 5 examples (streaming):\")\n # count = 0\n # for example in dataset:\n # if count >= 5:\n # break\n # print(f\" Example {count+1}: Caption - {example['caption'][:50]}...\")\n # # Process example['image'] and example['caption']\n # count += 1\n \n ```\n > *Note: Ensure you have enough disk space for the Hugging Face cache if not using `streaming=True`.*\n\n### Citation\n\nIf you use this dataset in your research or challenge participation, please cite the following paper describing the curation method:\n\n```\n@misc{rodríguezdevera2024precisionscaledomainspecificdatasets,\n title={Precision at Scale: Domain-Specific Datasets On-Demand},\n author={Jesús M Rodríguez-de-Vera and Imanol G Estepa and Ignacio Sarasúa and Bhalaji Nagarajan and Petia Radeva},\n year={2024},\n eprint={2407.03463},\n archivePrefix={arXiv},\n primaryClass={cs.CV},\n url={https://arxiv.org/abs/2407.03463},\n}\n```\n\n# Test Data - Files Provided\n\n* **Test1 Folder** - Multi-label test set. It contains all images, captions (TXT) and image order (TXT).\n* **Test2 Folder** - Single-label test set. It contains all images, captions (JSON) and image order (TXT).\n* **Baseline** - Baseline Python scripts with SigLIP inferences for both tests.\n* **npz_to_submission.py** - A simple python script that transforms predictions to submission format.\n* **sample_submission.csv** - A sample submission file in the correct format. \n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "The challenge will be divided in two different phases. \n## Phase One\nPhase one, which is common for all participants, involves two public test sets. For the first test set, participants are encouraged to link every image to N captions. Note that N could range from 0 to the total number of captions in the test set. This linkage should be provided in a **sparse matrix index format**. \nThe results matrix of this test set would be as follows:\n\n| | C0 | C1 | C2 | C3 | C4 | C5 |\n| --- | --- | --- | --- | --- | --- | --- |\n| I0 | 1 | 0 | 1 | 1 | 0 | 0 |\n| I1 | 0 | 1 | 0 | 1 | 1 | 0 |\n| I2 | 1 | 1 | 0 | 0 | 1 | 0 |\n\n\nFor the second test set, the format should be the exact same. However, each image will only have a single correct caption. This way, the results matrix would look like:\n\n| | C0 | C1 | C2 | C3 | C4 | C5 |\n| --- | --- | --- | --- | --- | --- | --- |\n| I0 | 1 | 0 | 0 | 0 | 0 | 0 |\n| I1 | 0 | 0 | 0 | 0 | 1 | 0 |\n| I2 | 0 | 0 | 1 | 0 | 0 | 0 |\n\nThe submission file must consist of a single CSV file with the prediction for the Test 1 and Test 2 tasks concatenated (Test 1 followed by Test 2). \n\nParticipants **must provide** a CSV file in the below **format**:\n\n`(I0,[C0, C2, C3])`\n`(I1,[C1, C3, C4])`\n`(I2,[C0, C1, C4])`\n`... Rest of Test 1`\n`(I0,[C0])`\n`(I1,[C4])`\n`(I2,[C2])`\n`... Rest of Test 2`\n\nwhere first column represents the first index number (row) and the second column contains the index of all predicted captions.\n\n\nThe Challenge provides a **submission file example** 'sample_submission.csv' to follow.\n\n> **The final evaluation score will be computed using the geometric mean of Test1 (F1-score) and Test2 (Accuracy) results.**\n\nBest 4 participants will move to Phase Two and they will be asked to provide information about the data used to train the model.\n\n## Phase Two\nIn this phase participants are required to submit their model, all relevant scripts and a txt file that contains the source of information used to train the model. Organizers will check for any limitations and rules violation and they will reproduce the results obtained by the provided model in Phase one. \nNote that **results that are not reproducible will lead to a disqualification**. \nAdditionally, we will evaluate all the models on our own private test set to decide the winner and runner-up. Selected Winner and Runner-up will be asked to **provide all the data used to train their model**.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "## Challenge License Agreement\n\n**1. Purpose and Scope** \nThis license governs the use of the data and models provided and used during the participation in the MetaFood'25 Challenge. The data is intended **solely for research and non-commercial purposes** in the context of the Challenge.\n\n**2. Composition of the Dataset** \nThe dataset used by the participants may include:\n\n- Data collected or synthesized by the organizers,\n- Publicly available datasets redistributed under their original licenses,\n- Synthetic or automatically generated annotations or captions.\n- Non-copyrighted and publicly available data.\n\nParticipants are reminded that some **public datasets** and publicly available data may have their own license terms. \nBy participating in the Challenge, you must **respect and comply** with the original licenses of these data, along with the challenge rules. \nAdditionally, [Precision at Scale](https://arxiv.org/abs/2407.03463) should be mentioned and cited for usage of the provided training data.\n\n**3. Permitted Uses of the provided data**\nParticipants are allowed to:\n\n- Download, store, and process the dataset for the purpose of developing and evaluating models for the Challenge,\n- Use the data solely for academic, educational, or research purposes within the context of the Challenge.\n\n**4. Prohibited Uses** \nParticipants are **not allowed** to:\n\n- Use the provided data for any commercial purpose,\n- Redistribute or republish the data, in whole or in part, except as part of challenge submissions,\n- Use **copyrighted or proprietary data** when training or augmenting their models for this Challenge. This includes both using own private data and data they do not have rights to. \n\n**5. External Data and Model Usage** \nParticipants are encouraged to use **external data** or pre-trained models, provided that:\n\n- The data is used in compliance with its respective license,\n- It does not violate copyright or intellectual property rights,\n- It is not derived from any source that would conflict with the rules or intent of this license.\n\n**6. Attribution and Citation** \nAny use or publication of results obtained using the dataset must include proper attribution to the Challenge and any original dataset providers.\n\n**7. Liability and Warranties** \nThe dataset is provided \"as-is\", without warranties of any kind. The organizers shall not be held liable for any damage or loss resulting from its use.\n\n**8. Termination** \nAny violation of the terms above may result in immediate disqualification from the Challenge and revocation of data access.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "abstract", "content": "\n## Problem\n\nThe goal of this challenge is to develop a Vision-Language Model (VLM) capable of accurately understanding and relating the visual cues of food dishes to their corresponding textual descriptions. This task pushes the boundaries of **fine-grained visual recognition and multimodal alignment**, especially in a challenging and diverse domain as food. Recognizing the subtle visual features that differentiate similar dishes, ingredients, and preparation styles is crucial for a wide range of applications from dietary tracking to restaurant automation.\n\nTo support participants in building strong models, we provide a **training set consisting of 400,000 food image-caption pairs** obtained by the [Precision at Scale framework](https://arxiv.org/abs/2407.03463). The dataset is a combination of **synthetic and noisy real captions**. Note that some of the images may also be synthetic. The data will be provided in a format that includes each caption along with a **link to download the associated image**. We strongly encourage all participants to **download the images as early as possible** and to **report any issues** they may encounter during the download process, so we can address them quickly. As some training-set images belong to LAION, there is a possibility that some of them are being removed by the authors during the course of the challenge. \n\nTo foster creativity, we allow participants to use **any external data sources** or pre-trained models (see \"Limitations\" and \"Rules\" for more information), as long as they **adhere to the license terms of this challenge and any third-party data** they incorporate. The focus is on achieving the **most accurate and detailed alignment between food images and text**, and we want to provide as much freedom as possible to explore different modeling strategies and data augmentation techniques.\n\nThe initial training data can be downloaded [from HuggingFace](https://huggingface.co/collections/jesusmolrdv/cvprw-mtf-2025-vlm-challenge-data-67e3b1cd766b4836df868a1b).\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "foundational-rules", "content": "The following Kaggle Competition Foundational Rules (“ Foundational Rules ”) apply to every competition regardless of whether the Sponsor creates competition-specific rules. Any competition-specific rules provided by the Sponsor are in addition to these rules, and in the case of any conflict or inconsistency, these Foundational Rules control and nullify contrary competition-specific rules.\n###GENERAL COMPETITION RULES - BINDING AGREEMENT\n####1. ELIGIBILITY\na. To be eligible to enter the Competition, you must be:\n1. a registered account holder at Kaggle.com; \n2. the older of 18 years old or the age of majority in your jurisdiction of residence (unless otherwise agreed to by Competition Sponsor and appropriate parental/guardian consents have been obtained by Competition Sponsor); \n3. not a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, or North Korea; and\n4. not a person or representative of an entity under U.S. export controls or sanctions (see: [https://www.treasury.gov/resourcecenter/sanctions/Programs/Pages/Programs.aspx][1]).\n\nb. Competitions are open to residents of the United States and worldwide, except that if you are a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, North Korea, or are subject to U.S. export controls or sanctions, you may not enter the Competition. Other local rules and regulations may apply to you, so please check your local laws to ensure that you are eligible to participate in skills-based competitions. The Competition Host reserves the right to forego or award alternative Prizes where needed to comply with local laws. If a winner is located in a country where prizes cannot be awarded, then they are not eligible to receive a prize.\n\nc. If you are entering as a representative of a company, educational institution or other legal entity, or on behalf of your employer, these rules are binding on you, individually, and the entity you represent or where you are an employee. If you are acting within the scope of your employment, or as an agent of another party, you warrant that such party or your employer has full knowledge of your actions and has consented thereto, including your potential receipt of a Prize. You further warrant that your actions do not violate your employer's or entity's policies and procedures. \n\nd. The Competition Sponsor reserves the right to verify eligibility and to adjudicate on any dispute at any time. If you provide any false information relating to the Competition concerning your identity, residency, mailing address, telephone number, email address, ownership of right, or information required for entering the Competition, you may be immediately disqualified from the Competition.\n\n####2. SPONSOR AND HOSTING PLATFORM\n\na. The Competition is sponsored by Competition Sponsor named above. The Competition is hosted on behalf of Competition Sponsor by Kaggle Inc. (\"Kaggle\"). Kaggle is an independent contractor of Competition Sponsor, and is not a party to this or any agreement between you and Competition Sponsor. You understand that Kaggle has no responsibility with respect to selecting the potential Competition winner(s) or awarding any Prizes. Kaggle will perform certain administrative functions relating to hosting the Competition, and you agree to abide by the provisions relating to Kaggle under these Rules. As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at [www.kaggle.com/terms][2] in addition to these Rules.\n\n####3. COMPETITION PERIOD\na. For the purposes of Prizes, the Competition will run from the Start Date and time to the Final Submission Deadline (such duration the “Competition Period”). The Competition Timeline is subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.\n\n####4. COMPETITION ENTRY\na. NO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website prior to the Entry Deadline, and follow the instructions for developing and entering your Submission through the Competition Website. Your Submissions must be made in the manner and format, and in compliance with all other requirements, stated on the Competition Website (the \"Requirements\"). Submissions must be received before any Submission deadlines stated on the Competition Website. Submissions not received by the stated deadlines will not be eligible to receive a Prize.\nb. Submissions may not use or incorporate information from hand labeling or human prediction of the validation dataset or test data records.\nc. If the Competition is a multi-stage competition with temporally separate training and/or test data, one or more valid Submissions may be required during each Competition stage in the manner described on the Competition Website in order for the Submissions to be Prize eligible.\nd. Submissions are void if they are in whole or part illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. Competition Sponsor reserves the right to disqualify any entrant who does not follow these Rules, including making a Submission that does not meet the Requirements. \n\n####5. INDIVIDUALS AND TEAMS\na. Individual Account. You may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website. \nb. Teams. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a Team; however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size stated on the Competition Website.\nc. Team Merger. Teams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules. \nd. Private Sharing. No private sharing outside of Teams. Privately sharing code or data outside of Teams is not permitted. It's okay to share code if made available to all Participants on the forums.\n\n####6. SUBMISSION CODE REQUIREMENTS\na. Private Code Sharing. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition Period, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data or other source or executable code relevant to the Competition (“Competition Code”). This prohibition includes sharing Competition Code between separate Teams, unless a Team merger occurs. Any such sharing of Competition Code is a breach of these Competition Rules and may result in disqualification.\nb. Public Code Sharing. You are permitted to publicly share Competition Code, provided that such public sharing does not violate the intellectual property rights of any third party. If you do choose to share Competition Code or other such code, you are required to share it on Kaggle.com on the discussion forum or notebooks associated specifically with the Competition for the benefit of all competitors. By so sharing, you are deemed to have licensed the shared code under an Open Source Initiative-approved license (see [www.opensource.org][3]) that in no event limits commercial use of such Competition Code or model containing or depending on such Competition Code.\nc. Use of Open Source. Unless otherwise stated in the Specific Competition Rules above, if open source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see [www.opensource.org][4]) that in no event limits commercial use of such code or model containing or depending on such code.\n\n####7. DETERMINING WINNERS\na. Each Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's Public Leaderboard. The potential winner(s) are determined solely by the leaderboard ranking on the Private Leaderboard, subject to compliance with these Rules. The Public Leaderboard will be based on the public test set and the Private Leaderboard will be based on the private test set.\nb. In the event of a tie, the Submission that was entered first to the Competition will be the winner. In the event a potential winner is disqualified for any reason, the Submission that received the next highest score rank will be chosen as the potential winner.\n\n####8. NOTIFICATION OF WINNERS & DISQUALIFICATION\na. The potential winner(s) will be notified by email. \nb. If a potential winner (i) does not respond to the notification attempt within one (1) week from the first notification attempt or (ii) notifies Kaggle within one week after the Final Submission Deadline that the potential winner does not want to be nominated as a winner or does not want to receive a Prize, then, in each case (i) and (ii) such potential winner will not receive any Prize, and an alternate potential winner will be selected from among all eligible entries received based on the Competition’s judging criteria.\nc. In case (i) and (ii) above Kaggle may disqualify the Participant. However, in case (ii) above, if requested by Kaggle, such potential winner may provide code and documentation to verify the Participant’s compliance with these Rules. If the potential winner provides code and documentation to the satisfaction of Kaggle, the Participant will not be disqualified pursuant to this paragraph.\nd. Competition Sponsor reserves the right to disqualify any Participant from the Competition if the Competition Sponsor reasonably believes that the Participant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other Participants, Competition Sponsor or Kaggle.\ne. A disqualified Participant may be removed from the Competition leaderboard, at Kaggle's sole discretion. If a Participant is removed from the Competition Leaderboard, additional winning features associated with the Kaggle competition platform, for example Kaggle points or medals, may also not be awarded.\nf. The final leaderboard list will be publicly displayed at Kaggle.com. Determinations of Competition Sponsor are final and binding.\n\n####9. PRIZES\na. Prize(s) are as described on the Competition Website and are only available for winning during the time period described on the Competition Website. The odds of winning any Prize depends on the number of eligible Submissions received during the Competition Period and the skill of the Participants. \nb. All Prizes are subject to Competition Sponsor's review and verification of the Participant’s eligibility and compliance with these Rules, and the compliance of the winning Submissions with the Submissions Requirements. In the event that the Submission demonstrates non-compliance with these Competition Rules, Competition Sponsor may at its discretion take either of the following actions: (i) disqualify the Submission(s); or (ii) require the potential winner to remediate within one week after notice all issues identified in the Submission(s) (including, without limitation, the resolution of license conflicts, the fulfillment of all obligations required by software licenses, and the removal of any software that violates the software restrictions).\nc. A potential winner may decline to be nominated as a Competition winner in accordance with Section 3.8.\nd. Potential winners must return all required Prize acceptance documents within two (2) weeks following notification of such required documents, or such potential winner will be deemed to have forfeited the prize and another potential winner will be selected. Prize(s) will be awarded within approximately thirty (30) days after receipt by Competition Sponsor or Kaggle of the required Prize acceptance documents. Transfer or assignment of a Prize is not allowed. \ne. You are not eligible to receive any Prize if you do not meet the Eligibility requirements in Section 2.7 and Section 3.1 above.\nf. If a Team wins a monetary Prize, the Prize money will be allocated in even shares between the eligible Team members, unless the Team unanimously opts for a different Prize split and notifies Kaggle before Prizes are issued.\n\n####10. TAXES\na. ALL TAXES IMPOSED ON PRIZES ARE THE SOLE RESPONSIBILITY OF THE WINNERS. Payments to potential winners are subject to the express requirement that they submit all documentation requested by Competition Sponsor or Kaggle for compliance with applicable state, federal, local and foreign (including provincial) tax reporting and withholding requirements. Prizes will be net of any taxes that Competition Sponsor is required by law to withhold. If a potential winner fails to provide any required documentation or comply with applicable laws, the Prize may be forfeited and Competition Sponsor may select an alternative potential winner. Any winners who are U.S. residents will receive an IRS Form-1099 in the amount of their Prize.\n\n####11. GENERAL CONDITIONS\na. All federal, state, provincial and local laws and regulations apply.\n\n####12. PUBLICITY\na. You agree that Competition Sponsor, Kaggle and its affiliates may use your name and likeness for advertising and promotional purposes without additional compensation, unless prohibited by law.\n\n####13. PRIVACY\na. You acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to, name, mailing address, phone number, and email address (“Personal Information”). Kaggle acts as an independent controller with regard to its collection, storage, sharing, and other use of this Personal Information, and will use this Personal Information in accordance with its Privacy Policy <[www.kaggle.com/privacy][6]>, including for administering the Competition. As a Kaggle.com account holder, you have the right to request access to, review, rectification, portability or deletion of any personal data held by Kaggle about you by logging into your account and/or contacting Kaggle Support at <[www.kaggle.com/contact][7]>.\nb. As part of Competition Sponsor performing this contract between you and the Competition Sponsor, Kaggle will transfer your Personal Information to Competition Sponsor, which acts as an independent controller with regard to this Personal Information. As a controller of such Personal Information, Competition Sponsor agrees to comply with all U.S. and foreign data protection obligations with regard to your Personal Information. Kaggle will transfer your Personal Information to Competition Sponsor in the country specified in the Competition Sponsor Address listed above, which may be a country outside the country of your residence. Such country may not have privacy laws and regulations similar to those of the country of your residence.\n\n####14. WARRANTY, INDEMNITY AND RELEASE \na. You warrant that your Submission is your own original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses. You agree not to make any Submission that: (i) infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; or (ii) otherwise violates any applicable U.S. or foreign state or federal law.\nb. To the maximum extent permitted by law, you indemnify and agree to keep indemnified Competition Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any of your acts, defaults or omissions and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the Competition Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules or any applicable U.S. or foreign state or federal law; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the Competition; and (e) your acceptance, possession, misuse or use of any Prize, or your participation in the Competition and any Competition-related activity.\nc. You hereby release Competition Entities from any liability associated with: (a) any malfunction or other problem with the Competition Website; (b) any error in the collection, processing, or retention of any Submission; or (c) any typographical or other error in the printing, offering or announcement of any Prize or winners.\n\n####15. INTERNET\na. Competition Entities are not responsible for any malfunction of the Competition Website or any late, lost, damaged, misdirected, incomplete, illegible, undeliverable, or destroyed Submissions or entry materials due to system errors, failed, incomplete or garbled computer or other telecommunication transmission malfunctions, hardware or software failures of any kind, lost or unavailable network connections, typographical or system/human errors and failures, technical malfunction(s) of any telephone network or lines, cable connections, satellite transmissions, servers or providers, or computer equipment, traffic congestion on the Internet or at the Competition Website, or any combination thereof, which may limit a Participant’s ability to participate.\n\n####16. RIGHT TO CANCEL, MODIFY OR DISQUALIFY\na. If for any reason the Competition is not capable of running as planned, including infection by computer virus, bugs, tampering, unauthorized intervention, fraud, technical failures, or any other causes which corrupt or affect the administration, security, fairness, integrity, or proper conduct of the Competition, Competition Sponsor reserves the right to cancel, terminate, modify or suspend the Competition. Competition Sponsor further reserves the right to disqualify any Participant who tampers with the submission process or any other part of the Competition or Competition Website. Any attempt by a Participant to deliberately damage any website, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws. Should such an attempt be made, Competition Sponsor and Kaggle each reserves the right to seek damages from any such Participant to the fullest extent of the applicable law.\n\n####17. NOT AN OFFER OR CONTRACT OF EMPLOYMENT\na. Under no circumstances will the entry of a Submission, the awarding of a Prize, or anything in these Rules be construed as an offer or contract of employment with Competition Sponsor or any of the Competition Entities. You acknowledge that you have submitted your Submission voluntarily and not in confidence or in trust. You acknowledge that no confidential, fiduciary, agency, employment or other similar relationship is created between you and Competition Sponsor or any of the Competition Entities by your acceptance of these Rules or your entry of your Submission.\n\n####18. DEFINITIONS\na. \"Competition Data\" are the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to Participants. \nb. An “Entry” is when a Participant has joined, signed up, or accepted the rules of a competition. Entry is required to make a Submission to a competition.\nc. A “Final Submission” is the Submission selected by the user, or automatically selected by Kaggle in the event not selected by the user, that is/are used for final placement on the competition leaderboard.\nd. A “Participant” or “Participant User” is an individual who participates in a competition by entering the competition and making a Submission.\ne. The “Private Leaderboard” is a ranked display of Participants’ Submission scores against the private test set. The Private Leaderboard determines the final standing in the competition.\nf. The “Public Leaderboard” is a ranked display of Participants’ Submission scores against a representative sample of the test data. This leaderboard is visible throughout the competition.\ng. A “Sponsor” is responsible for hosting the competition, which includes but is not limited to providing the data for the competition, determining winners, and enforcing competition rules.\nh. A “Submission” is anything provided by the Participant to the Sponsor to be evaluated for competition purposes and determine leaderboard position. A Submission may be made as a model, notebook, prediction file, or other format as determined by the Sponsor.\ni. A “Team” is one or more Participants participating together in a Kaggle competition, by officially merging together as a Team within the competition platform.\n\n [1]: https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx\n [2]: http://www.kaggle.com/terms\n [3]: http://www.opensource.org\n [4]: http://www.opensource.org\n [5]: https://www.kaggle.com/WinningModelDocumentationGuidelines\n [6]: http://www.kaggle.com/privacy\n [7]: http://www.kaggle.com/contact\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Limitations", "content": "To maintain the challenge as fair as possible, we introduce a few limitations:\n- Models used need to **fit in a 80GB GPU**. If any quantization or preprocessing is required, the script should be provided. Participants can use techniques such as distillation is found apt, however, the final submitted model should adhere to the limitations and the weights of the larger models should be made available, is passed to phase 2.\n- Automatic or hand-made heuristics are allowed for both training and evaluation, however, the code should be uploaded on phase two. Remember the same heuristics should be applied for all evaluations. \n- The total evaluation time for both test sets provided should never pass **1 hour limit**. We will take a single NVIDIA H100 GPU time as reference.\n- Each team is allowed to have a maximum of 5 participants.\n- Maximum daily submissions limit is 10.\n- Challenge Data License Agreement must be strictly followed.\n- Test set images should not be used for training purposes. Participants should ensure that these images are removed from any external data source used as training.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Challenge License", "content": "All participants must read and adhere to the Challenge License (See Rules tab). \nBy joining the challenge, the participants agree to follow the rules and regulations for all submissions done to the Challenge", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }