Wheat detection using Faster RCNN

Image generation with copy-paste for global wheat detection proposed by Najafian et al., 2021

RetinaNet for Object Detection in TensorFlow2 and Applications

Autoencoder based approach for the mitigation of spurious correlations on YOLOv5 detections

global wheat detection

This project includes my (31st place) solution to the 2021 Global Wheat Challenge on AICrowd. The solution is based on self-supervised learning and the Swin Transformer. The repo is forked from the original implementation of the Swin-transformer for object detection.