English

Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation

Computer Vision and Pattern Recognition 2021-04-13 v1

Abstract

This paper addresses the task of unsupervised video multi-object segmentation. Current approaches follow a two-stage paradigm: 1) detect object proposals using pre-trained Mask R-CNN, and 2) conduct generic feature matching for temporal association using re-identification techniques. However, the generic features, widely used in both stages, are not reliable for characterizing unseen objects, leading to poor generalization. To address this, we introduce a novel approach for more accurate and efficient spatio-temporal segmentation. In particular, to address \textbf{instance discrimination}, we propose to combine foreground region estimation and instance grouping together in one network, and additionally introduce temporal guidance for segmenting each frame, enabling more accurate object discovery. For \textbf{temporal association}, we complement current video object segmentation architectures with a discriminative appearance model, capable of capturing more fine-grained target-specific information. Given object proposals from the instance discrimination network, three essential strategies are adopted to achieve accurate segmentation: 1) target-specific tracking using a memory-augmented appearance model; 2) target-agnostic verification to trace possible tracklets for the proposal; 3) adaptive memory updating using the verified segments. We evaluate the proposed approach on DAVIS17_{17} and YouTube-VIS, and the results demonstrate that it outperforms state-of-the-art methods both in segmentation accuracy and inference speed.

Keywords

Cite

@article{arxiv.2104.04782,
  title  = {Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation},
  author = {Tianfei Zhou and Jianwu Li and Xueyi Li and Ling Shao},
  journal= {arXiv preprint arXiv:2104.04782},
  year   = {2021}
}

Comments

CVPR21

R2 v1 2026-06-24T01:02:13.682Z