Improving Semantic Segmentation via Decoupled Body and Edge Supervision

by   Xiangtai Li, et al.

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for semantic segmentation is proposed. Our insight is that appealing performance of semantic segmentation requires explicitly modeling the object body and edge, which correspond to the high and low frequency of the image. To do so, we first warp the image feature by learning a flow field to make the object part more consistent. The resulting body feature and the residual edge feature are further optimized under decoupled supervision by explicitly sampling different parts (body or edge) pixels. We show that the proposed framework with various baselines or backbone networks leads to better object inner consistency and object boundaries. Extensive experiments on four major road scene semantic segmentation benchmarks including Cityscapes, CamVid, KIITI and BDD show that our proposed approach establishes new state of the art while retaining high efficiency in inference. In particular, we achieve 83.7 mIoU % on Cityscape with only fine-annotated data. Code and models are made available to foster any further research (<>).


page 2

page 12

page 13

page 18

page 19

page 20


Multi-Plateau Ensemble for Endoscopic Artefact Segmentation and Detection

Endoscopic artefact detection challenge consists of 1) Artefact detectio...

JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds

Semantic segmentation and semantic edge detection can be seen as two dua...

Efficient Segmentation: Learning Downsampling Near Semantic Boundaries

Many automated processes such as auto-piloting rely on a good semantic s...

Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings

Semantic segmentation is a computer vision task that associates a label ...

Conditional Reconstruction for Open-set Semantic Segmentation

Open set segmentation is a relatively new and unexploredtask, with just ...

Learning to Segment Human Body Parts with Synthetically Trained Deep Convolutional Networks

This paper presents a new framework for human body part segmentation bas...

Coarse-to-Fine Feature Mining for Video Semantic Segmentation

The contextual information plays a core role in semantic segmentation. A...

Please sign up or login with your details

Forgot password? Click here to reset