Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation

2023-10-27 · Son Nguyen, Mikel Lainsa, Hung Dao, Daeyoung Kim, Giang Nguyen

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.

📄 PDF Abstract BibTeX arXiv:2310.17949

Code (1)

nguyendinhson-kaist/mmsports23-seg-autoid 공식 구현 pytorch

Tasks

Data Augmentation Instance Segmentation Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Stochastic Weight Averaging Stochastic Weight Averaging is an optimization procedure that averages multiple points along the trajectory of SGD, with a cyclical or…

Geometry-Aware Recurrent Neural Networks for Active Visual Recognition

2018-11-03 · NeurIPS 2018 12 · Ricson Cheng, Ziyan Wang, Katerina Fragkiadaki

We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations…

3D Reconstruction Object object-detection Object Detection+1

3D-Aware Instance Segmentation and Tracking in Egocentric Videos

2024-08-19 · Yash Bhalgat, Vadim Tschernezki, Iro Laina, João F. Henriques 외

Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility. This paper introduces a novel approach to instance segmentatio…

3D Object Reconstruction Instance Segmentation Object Object Reconstruction+5

EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting

2025-03-14 · Di Li, Jie Feng, Jiahao Chen, Weisheng Dong 외

Egocentric scenes exhibit frequent occlusions, varied viewpoints, and dynamic interactions compared to typical scene understanding tasks. Occlusions and varied viewpoints can lead to multi-view semantic inconsistencies, …

Scene Understanding Segmentation

Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image

2019-06-18 · Matthieu Grard, Emmanuel Dellandréa, Liming Chen

Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous l…

Boundary Detection Decoder Instance Segmentation Semantic Segmentation

SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentation

2023-03-14 · CVPR 2023 1 · Ruihuang Li, Chenhang He, Yabin Zhang, Shuai Li 외

Weakly supervised instance segmentation using only bounding box annotations has recently attracted much research attention. Most of the current efforts leverage low-level image features as extra supervision without expli…

Box-supervised Instance Segmentation Instance Segmentation Segmentation Semantic Segmentation+1