Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation
This work addresses occlusion challenges in instance segmentation for sports analytics, specifically in basketball, but is incremental as it builds on existing methods like HTC and data augmentation.
The paper tackles instance segmentation under occlusions in basketball by proposing a location-aware copy-paste data augmentation technique and using a Hybrid Task Cascade framework, achieving an occlusion score of 0.533 and ranking first in the ACM MMSports 2023 competition.
Occlusion is a long-standing problem in computer vision, particularly in instance segmentation. ACM MMSports 2023 DeepSportRadar has introduced a dataset that focuses on segmenting human subjects within a basketball context and a specialized evaluation metric for occlusion scenarios. Given the modest size of the dataset and the highly deformable nature of the objects to be segmented, this challenge demands the application of robust data augmentation techniques and wisely-chosen deep learning architectures. Our work (ranked 1st in the competition) first proposes a novel data augmentation technique, capable of generating more training samples with wider distribution. Then, we adopt a new architecture - Hybrid Task Cascade (HTC) framework with CBNetV2 as backbone and MaskIoU head to improve segmentation performance. Furthermore, we employ a Stochastic Weight Averaging (SWA) training strategy to improve the model's generalization. As a result, we achieve a remarkable occlusion score (OM) of 0.533 on the challenge dataset, securing the top-1 position on the leaderboard. Source code is available at this https://github.com/nguyendinhson-kaist/MMSports23-Seg-AutoID.