RefineVIS: Video Instance Segmentation with Temporal Attention Refinement
This work addresses the problem of accurate and consistent instance segmentation in videos for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles video instance segmentation by introducing RefineVIS, a framework that uses temporal attention refinement and contrastive learning to improve object association and segmentation accuracy, achieving state-of-the-art results of 64.4 AP on YouTube-VIS 2019, 61.4 AP on YouTube-VIS 2021, and 46.1 AP on OVIS.
We introduce a novel framework called RefineVIS for Video Instance Segmentation (VIS) that achieves good object association between frames and accurate segmentation masks by iteratively refining the representations using sequence context. RefineVIS learns two separate representations on top of an off-the-shelf frame-level image instance segmentation model: an association representation responsible for associating objects across frames and a segmentation representation that produces accurate segmentation masks. Contrastive learning is utilized to learn temporally stable association representations. A Temporal Attention Refinement (TAR) module learns discriminative segmentation representations by exploiting temporal relationships and a novel temporal contrastive denoising technique. Our method supports both online and offline inference. It achieves state-of-the-art video instance segmentation accuracy on YouTube-VIS 2019 (64.4 AP), Youtube-VIS 2021 (61.4 AP), and OVIS (46.1 AP) datasets. The visualization shows that the TAR module can generate more accurate instance segmentation masks, particularly for challenging cases such as highly occluded objects.