.png){kind=icon}
.png){kind=icon}
Return
UniInst: Unique representation for end-to-end instance segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2022.09.112.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Existing instance segmentation methods have achieved impressive performance but still suffer from a common dilemma: redundant representations (e.g., multiple boxes, grids, and anchor points) are inferred for one instance, which leads to multiple duplicated predictions. Thus, mainstream methods usually rely on a hand-designed non-maximum suppression (NMS) post-processing step to select the optimal predic-tion result, consequently hindering end-to-end training. To address this issue, we propose a box-free and NMS-free end-to-end instance segmentation framework, dubbed UniInst, which yields only one unique representation for each instance. Specifically, we design an instance-aware one-to-one assignment scheme, named Only Yield One Representation (OYOR). It dynamically assigns one unique representation to each instance according to the matching quality between predictions and ground truths. Then, a novel prediction re-ranking strategy is elegantly integrated into the framework to address the misalignment between the classification score and mask quality, enabling the learned representation to be more dis-criminative. With these techniques, our UniInst, the first FCN-based box-free and NMS-free end-to-end instance segmentation framework, achieves competitive performance, e.g., 39.0 mask AP using ResNet-50-FPN and 40.2 mask AP using ResNet-101-FPN on COCO test-dev. Moreover, the proposed instance-aware method is robust to occlusion scenes because of non-dependent on box and NMS. It out-performs common baselines by remarkable mask AP on the heavily-occluded OCHuman benchmark. Code is available at https://github.com/b03505036/UniInst.(c) 2022 Published by Elsevier B.V.
Keywords:
Instance segmentation
End-to-end instance segmentation
Fully convolutional networks
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W