Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation

Xiaolin Hu, Xiao Li, Zhaoxiang Zhang, Jianmin Li, Hang Chen, Chufeng Tang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

• tinyalpha/BPR — marked official in Papers with Code; named in the paper
• pideyi1025/DeepLabV3Plus-RailSem19

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Following the idea of looking closer to segment boundaries better, we extract and refine a series of small boundary patches along the predicted instance boundaries. The refinement is accomplished by a boundary patch refinement network at higher resolution. The proposed BPR framework yields significant improvements over the Mask R-CNN baseline on Cityscapes benchmark, especially on the boundaryaware metrics. Moreover, by applying the BPR framework to the "PolyTransform + SegFix" baseline, we reached 1 st place on the Cityscapes leaderboard. Code is available at https://github.com/tinyalpha/BPR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.05239")
get_code_for_paper("2104.05239")
have("2104.05239")

Connect an agent — have() is free.