2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge
This work addresses data shortage in object detection for computer vision researchers, but it is incremental as it combines existing techniques without introducing new methods.
The paper tackled the problem of object detection with limited training data by applying state-of-the-art data augmentation, model designs, and post-processing ensemble methods, achieving 36.6% AP on the COCO 2017 validation set using only 10K images and ranking 2nd in the challenge.
In this report, we descibe our approach to the ECCV 2020 VIPriors Object Detection Challenge which took place from March to July in 2020. We show that by using state-of-the-art data augmentation strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. Notably, our overall detection system achieves 36.6$\%$ AP on the COCO 2017 validation set using only 10K training images without any pre-training or transfer learning weights ranking us 2nd place in the challenge.