#Important Information Please contact me (robeson1010@gmail.com) to verify the your results on our private dataset. We will award and certification after evaluation at August 18, 2024. @Vietnamese @Nguyen Hoang Anh 2903 @ElyyLong Trương @In Processing @Long Trương @ElonMusk113 # Overview The International Conference on Pattern Recognition (ICPR) 2024 Competition on “**Beyond Visible Spectrum: AI for Agriculture**” presents an exciting opportunity for researchers and practitioners to advance computer vision techniques in agricultural crop disease monitoring. By leveraging the vast multi/hyper spectral remote sensing image datasets, participants are encouraged to develop innovative deep learning algorithms. The primary aim is to enhance the accuracy and efficiency of identifying crop diseases, thereby contributing to sustainable agricultural practices and global food security. Participants in this challenge will have the chance to contribute to significant advancements in precision farming and crop monitoring techniques. By improving the deep learning vision models, the competition aims to drive forward the capabilities of agricultural technology, making it more efficient, accurate, and sustainable. The ICPR 2024 Competition on “Beyond Visible Spectrum” is not just a competition; it is a call to action for the computer research community to bring about transformative changes in how agricultural data is analyzed and utilized, paving the way for smarter, more sustainable farming practices that can benefit communities worldwide. In this competition, participants are challenged to employ self-supervised learning techniques to identify various types of crop diseases from remote sensing imagery. This task addresses the issue of limited labelled data in remote agricultural regions and encourages the development of models capable of learning meaningful representations without extensive annotated datasets. Self-supervised learning, at its core, revolves around an auxiliary task, often referred to as a pretext task, which utilizes auto-generated labels to guide the initialization of model parameters. These parameters are subsequently employed to enhance performance on downstream tasks such as classification, segmentation, and object detection. In essence, self-supervised learning entails two primary stages: the pretext task and real downstream tasks. The pretext task involves training a network in a self-supervised manner, leveraging auto-generated labels derived from unlabelled data to initialize model parameters effectively. By optimizing this objective through carefully designed pretext tasks, the network acquires the capability to extract meaningful representations from the input data. Subsequently, the trained network can be seamlessly transferred to supervised downstream tasks for real-world applications (e.g. classification tasks), where it can further enhance performance based on the learned representations [1-2]. For this challenge, we will provide a substantial remote sensing datasets covering arable land areas, which includes multi-spectral and synthetic aperture radar data (Sentinel 1/2). This dataset contains 500,000 images for participants to train their self-supervised models. Then a crop disease classification task and datasets will be established, covering wheat stripe rust, aphids, and rice blast and planthoppers. Participants use this data to fine turn their self-supervised models. The competition determines the performance of a self-supervised model by evaluating how much its performance improves over a model that does not use the self-supervised training dataset. [1. A generic Self-Supervised Learning (SSL) framework for representation learning from spectral–spatial features of unlabeled remote sensing imagery.](https://doi.org/10.3390/rs15215238) [2. The self-supervised spectral–spatial vision transformer network for accurate prediction of wheat nitrogen status from UAV imagery.](https://doi.org/10.3390/rs14061400) # Competition Schedule **Launch Date:** April 15, 2024 **Submission Opening:** April 15, 2024 **Submission Deadline:** July 21, 2024 **Submission of Competition Reports Deadline:** August 18, 2024 # Awards All submissions before the deadline will receive a participation certificate The top three places of each task will be awarded prizes to the value of: **1st Place:** $300 **2nd Place:** $200 **3rd Place:** $100 # Challenge keywords Remote sensing; Hyperspectral; Crop disease; Self-supervised learning; Crop disease; Deep learning # Workshop/conference This challenge is part of the conference on "The International Conference on Pattern Recognition (ICPR) (2024)".