According to Alan Turing, he believed that machines would be able to outperform humans if trained and taught to learn certain skills. With the rapid development of Artificial Intelligence, it is evident that it has undeniably become a part of our daily lives. Whether it's a simple task such as asking voice assistants to wake us up at seven a.m. or even using chatbots to book appointments, it demonstrates how artificial intelligence is capable of possessing human cognitive abilities. Additionally, computer vision is a field of artificial intelligence that has amassed much interest over the past few years because it enables the computer to comprehend images similarly to how human eyes perceive and process information. In contrast, humans took years to learn context from their environments, meanwhile, an algorithm can achieve the same by learning and training on a large collection of images called datasets.\n
","metadata":{}},{"cell_type":"markdown","source":"\n In order for computer vision to analyze and distinguish images, achieving a level of perception similar to humans, it relies on a substantial amount of image data to learn from. By providing the machine with sufficient data, it will be capable of self-learning without being programmed by someone. For instance, Apple's Face ID requires users to move their heads to display different angles of their faces to enable recognition. Furthermore, another example can be seen in Facebook's tagging algorithm when users post images, and the algorithm can recognize the user in different images even if they are posted by others. This is because the algorithm has been trained with multiple images of the user's face and has learned to recognize it. As a result, this demonstrates the importance of datasets in computer vision.\n
","metadata":{}},{"cell_type":"markdown","source":"\n\n A notable observation pertaining to the contribution of open datasets such as Common Objects in Context (COCO) and ImageNet is the increase in the number and availability of datasets, which contributes to the acceleration of research within the field by providing a diverse array of images for algorithm training purposes. Researchers now have access to a wider range of datasets, enabling them to explore different domains and enhance model performance. Some of the popular datasets include:\n
\n\n\n - Common Objects in Context (COCO): A large-scale object detection, segmentation, and captioning dataset.
\n - ImageNet: An image database organized according to the WordNet hierarchy (currently only the nouns), in which each node of the hierarchy is depicted by hundreds and thousands of images.
","metadata":{}},{"cell_type":"markdown","source":"","metadata":{},"attachments":{"080bafc4-e3e6-43bb-bf74-870cdef4cfe7.jpg":{"image/jpeg":"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"}}},{"cell_type":"markdown","source":"\n#### 1.4. Evaluation and Benchmarking\n\nIn the field of machine learning, benchmarking allows researchers to evaluate the performance of their models by measuring them against existing benchmarks. Moreover, specific benchmarks have been developed for different computer vision tasks. For example, KITTI for image segmentation, ObjectNet for image classification, and ADE20K for scene understanding. Notably, as evident from this histogram, popular datasets tend to have more benchmarks when compared to less popular datasets. However, it is important to note that not all dataset benchmarks accurately depict the real world, creating biases in the evaluation process.\n
","metadata":{}},{"cell_type":"markdown","source":"\n### 2. Our methodology\n\nOur notebook will focus on answering a number of research questions related to datasets used for Computer Vision papers:
\n - Why are researchers using older image datasets compared to newer ones?
\n - What advantages do newer datasets bring?
\n - What datasets are used in the current publications?
\n
\n
Every year, thousands of papers are being released. We made use of the Scopus Database to access the papers and collect reference information, which is later used in the data analysis stage. It is nearly impossible to analyze the datasets used in all those papers. Hence, we created a sample of approximately 850 research papers, using the following query parameters to filter:\n
\n - Publication Year: 2021 and 2022 (As to comply with Kaggle’s 2 year policy)
\n - “Computer” and “Vision” keywords present in the Title, Abstract or Keywords.
\n - Classified in the “Computer Science” Subject Area. Source: Only titles Published in IEEE. (This database contained the vast majority of highly cited papers related to Computer Vision. This query parameter ensures the quality of the surveyed papers).
\n
\nHowever, the total of approximately 850 papers is still a lot for a normal person to download and analyze. Thus, we built an autonomous program to download and analyze papers. It includes the following steps:\n
\n - Downloads a certain number of papers
\n - Analyzes the datasets used in those papers
\n - Writes the paper title together with the dataset name in the CSV file
\n - Removes the previously downloaded/analyzed papers(to save space)
\n - Repeats step 1
\n
\n
We have analyzed approximately 850 IEEE accepted papers from the years 2021 and 2022, which relate to Computer Vision.\n\nThis analysis will be automated with the aid of one of OpenAI's deep learning language models. After the data collection stage, we will perform a statistical approach using R to explore different patterns in the data and draw conclusions. Firstly, we will transform the data according to the tidy data convention and then generate meaningful visualizations.\n
\n\nWe used the following prompt to generate the dataset from the downloaded papers.
\n\n\"From the paper in the context, extract the following information: Datasets used for training of the computer vision model presented in the paper, year of release of the Datasets used for training of the computer vision model presented in the paper (This corresponds to the publication year of the citation pointing to the dataset). If there are multiple datasets, include all of them. Generate your response strictly in a csv format, where each entry represents a database and do not include anything else. If there is no information about the release year of the dataset substitute it by null. For example, your response can look like (without the quotes): 'Dataset name 1:null,Dataset name 2:2002'. Here Dataset name 1 has an unknown release date, and Dataset2 is released in 2002. There should be no other text in your response apart from the names of the datasets and the release years. Only include datasets that are specifically mentioned in the paper. Do not include any other datasets.\"
\n\nHowever, the resulted dataset was raw and required the data wrangling. Thus, we had to perform the pre-processing before the actual analysis.
","metadata":{}},{"cell_type":"markdown","source":"\n### 3. Factor analysis\n\n\nOur comprehensive analysis of the gathered data has elucidated the answers to the posed questions by demonstrating the significance of the different patterns in datasets used by researchers in their publications. These findings have greatly helped us in further discussions and exploration, which will be presented in the following subsections.\n
","metadata":{}},{"cell_type":"markdown","source":"\n#### 3.1. What datasets are being used in the current publications?\n\n","metadata":{}},{"cell_type":"code","source":"options(repr.plot.width = 20, repr.plot.height = 8)\n\ngraph1 <- df %>% drop_na(Year) %>% \n ggplot(aes(x = as.numeric(DatasetYear), y = Year)) +\n geom_jitter(aes(size = Cited.by, color = as.character(Year)), \n height = 0.3, width = 0.5, alpha = 0.7, na.rm = TRUE) +\n labs(\n title = \"Paper publication year compared to year of dataset used\",\n size = \"Number of citations\",\n color = \"Paper publication\"\n ) +\n xlab(\"Year of Dataset\") + ylab(\"Paper publication date\") +\n scale_y_continuous(breaks = seq(2021, 2022)) +\n scale_x_continuous(breaks = seq(2000, 2023, by = 5))\n\ngraph2 <- df %>% drop_na(DatasetYear, Year) %>% \n ggplot(aes(x = as.numeric(DatasetYear), y = as.character(Year))) +\n geom_boxplot(aes(fill = as.character(Year)), alpha = 0.8, show.legend = FALSE) +\n xlab(\"Year of Dataset\") + ylab(\"Paper publication date\") +\n labs(title = \"Paper publication year compared to year of dataset used\")\n\n# Arrange the graphs side by side with more spacing\ngrid.arrange(graph1, graph2, ncol = 2, widths = c(0.6, 0.6))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-07-16T19:10:15.618535Z","iopub.execute_input":"2023-07-16T19:10:15.643028Z","iopub.status.idle":"2023-07-16T19:10:16.681951Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n It is clear from the collected data that there has been a higher number of Computer Vision papers written in 2021 compared to more recent papers from 2022. The papers from 2021 are also more influential in terms of the number of citations. These papers from 2021 tend to use older Datasets. Thus,it is interesting to notice that while papers from 2021 have a more spare distribution of datasheet years, the ones from 2002, even though they are more concentrated in newer years, also have the highest year range. \n
","metadata":{}},{"cell_type":"code","source":"library(ggplot2)\n\ndts <- as.data.frame(table(df$DatasetName))\notherCount <- sum((dts$Freq < 6) * dts$Freq)\nfinalDts <- rbind(dts %>% filter(Freq > 6), data.frame(Var1 = \"Other\", Freq = otherCount))\n\n# Remove the \"Other\" category from finalDts\nfinalDts <- finalDts[finalDts$Var1 != \"Other\", ]\n\n# Calculate the percentage values\npercentages <- round(finalDts$Freq / sum(finalDts$Freq) * 100, 1)\n\n# Create the pie chart with percentage labels\npie(finalDts$Freq, labels = paste(finalDts$Var1, percentages, \"%\"), main = \"Most frequently used datasets\")\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-07-16T19:10:16.684102Z","iopub.execute_input":"2023-07-16T19:10:16.685288Z","iopub.status.idle":"2023-07-16T19:10:16.887614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As we can see in the pie chart, among the popular datasets, it is clear that most of the papers from the recent years used Coco and ImageNet the most. The Coco dataset was released in 2014. However, due to the recent update, people are still using Coco for evaluation and benchmarking their models. The similar thing goes for the ImageNet. Coco is a dataset targeted for evaluating the image segmentation models. Meanwhile, the ImageNet is mostly used for the classification training. Hence, from this analysis, we can observe that the researchers are tending to work on the image segmentation over the classification problems.
","metadata":{}},{"cell_type":"markdown","source":"","metadata":{},"attachments":{"3b6a3129-9e85-492c-8a6f-06bd75815a87.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"An unexpected finding was that even though there were a few popular datasets used by many papers, the datasets utilized in literature are very diverse. In the below chart, the \"other\" category presents the combined use of datasets that are mentioned fewer than 6 times. We can see that this category is the most numerous one. This reveals that while some benchmark datasets exist, researchers often don't settle on the most popular dataset; instead, they tend to use less well-known datasets, possibly because these datasets better fit their specific applications.
\n","metadata":{}},{"cell_type":"markdown","source":"\n#### 3.2. Why are researchers using older image datasets compared to newer ones?\n","metadata":{}},{"cell_type":"code","source":"suppressWarnings({\n df %>% drop_na(DatasetYear) %>% ggplot(aes(x = DatasetYear)) + geom_histogram(stat=\"count\", color = \"#000000\", fill = \"#0099F8\") +\n labs(\n title = \"Number of papers using datasets from each year\"\n) + xlab(\"Year of dataset used\") + ylab(\"Number of papers\")\n })","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-07-16T19:10:16.891070Z","iopub.execute_input":"2023-07-16T19:10:16.892665Z","iopub.status.idle":"2023-07-16T19:10:17.205211Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"A deeper understanding of this can be gained by examining further into the evaluation and benchmark section. Researchers often opt for older datasets due to benchmark purposes given that there already exist so many well-established dataset benchmarks to evaluate and measure the accuracy of their model’s performance. By using the existing benchmark, it allows researchers to see better comparability, accuracy, and reproducibility within their model. On the other hand, using newer datasets raises more challenges such as lack of familiarity, available resources and time consumption. However, this should not be interpreted as a limitation on the utilization of new datasets or judgment to their quality. In conclusion, it signifies that researchers consider multiple factors and adopt a careful approach to select the most appropriate datasets for their research.\n
","metadata":{}},{"cell_type":"markdown","source":"\n#### 3.3. What advantages do newer datasets bring??\n\nOne notable advantage newer datasets have over old ones is that they are up-to-date with the current trends and events of the world, enabling researchers to explore the latest research problems and potentially achieve better model performance. Moreover, newer datasets tend to have improved annotations with more detail and accuracy, which also address specific problems more effectively.\n
","metadata":{}},{"cell_type":"markdown","source":"\n### 4. Conclusion\n\nComparative Analysis on Datasets\nIn conclusion, we can come up with the analysis that researchers often prefer using the old benchmark datasets, specifically ImageNet and Coco. Additionally, it was observed that many research papers utilized non-benchmark datasets to evaluate model performance, which could lead to the potential biasness in their research outcomes.
\n\nAutonomous Literature Review\nThe literature review is one of the challenges in performing research. Reading and summarizing the papers is a time consuming task. Thus, we came up with an idea to speed up the process by creating the autonomous program that helped us to analyze the papers effectively and efficiently. We do believe that researchers can apply the similar technique to reduce the time consumption of the literature review in their research. \n \n We are very grateful to contribute something useful to the community.
","metadata":{}},{"cell_type":"markdown","source":"\n### 5. References\nWeinreich, Harald, et al. \"Not quite the average: An empirical study of Web use.\" ACM Transactions on the Web (TWEB) 2.1 (2008): 1-31.\n\nDenton, Emily, et al. \"Bringing the people back in: Contesting benchmark machine learning datasets.\" arXiv preprint arXiv:2007.07399 (2020).\n\nhttps://www.kaggle.com/datasets/mateuszalicante/cvdatasets\n\nhttps://www.activeloop.ai/resources/lacking-good-computer-vision-benchmark-datasets-is-a-problem-lets-fix-that/\n\n","metadata":{}},{"cell_type":"markdown","source":"Submission
","metadata":{}},{"cell_type":"code","source":"submission <- read.csv(\"/kaggle/input/2023-kaggle-ai-report/sample_submission.csv\")\nhead(submission)","metadata":{"execution":{"iopub.status.busy":"2023-07-16T19:10:17.208697Z","iopub.execute_input":"2023-07-16T19:10:17.209908Z","iopub.status.idle":"2023-07-16T19:10:17.247434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission[1, \"value\"] <- \"Image and/or video data\"\nsubmission[2, \"value\"] <- \"https://www.kaggle.com/code/kaungmyatkyaw/antique-enthusiasts-image-and-or-video-data\"\nsubmission[3, \"value\"] <- \"https://www.kaggle.com/code/radbear/advances-in-ai-vision-models-in-the-last-two-years/comments#2337375\"\nsubmission[4, \"value\"] <- \"https://www.kaggle.com/code/pandoraalias/unleashing-visual-intelligence-vid-img/comments#2337392\"\nsubmission[5, \"value\"] <- \"https://www.kaggle.com/code/sabrinahan/kaggle-image-and-video-related-ai-report/comments#2345823\"\n\nhead(submission)\n","metadata":{"execution":{"iopub.status.busy":"2023-07-16T19:10:17.250391Z","iopub.execute_input":"2023-07-16T19:10:17.251484Z","iopub.status.idle":"2023-07-16T19:10:17.278192Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"write.csv(submission, file = 'submission.csv', row.names = FALSE)\nsubmission <- read.csv(\"/kaggle/working/submission.csv\")\nhead(submission)","metadata":{"execution":{"iopub.status.busy":"2023-07-16T19:10:17.281270Z","iopub.execute_input":"2023-07-16T19:10:17.282373Z","iopub.status.idle":"2023-07-16T19:10:17.305282Z"},"trusted":true},"execution_count":null,"outputs":[]}]}