# Improving Semantic Segmentation via Decoupled Body and Edge Supervision

arXiv: https://arxiv.org/abs/2007.10035 · HTML: https://mlsanity.com/paper/2007.10035/

## Key facts

- Cited by 99 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 30 of 99)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)
- [Deep Hierarchical Semantic Segmentation](https://mlsanity.com/paper/2203.14335/) (2022)
- [OMG-Seg: Is One Model Good Enough For All Segmentation?](https://mlsanity.com/paper/2401.10229/) (2024)
- [Learning Statistical Texture for Semantic Segmentation](https://mlsanity.com/paper/2103.04133/) (2021)
- [Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks](https://mlsanity.com/paper/2112.01715/) (2021)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review](https://mlsanity.com/paper/2305.05813/) (2023)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow](https://mlsanity.com/paper/2109.09406/) (2021)
- [Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation](https://mlsanity.com/paper/2204.04655/) (2022)
- [Learning Implicit Feature Alignment Function for Semantic Segmentation](https://mlsanity.com/paper/2206.08655/) (2022)
- [PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation](https://mlsanity.com/paper/2103.06564/) (2021)
- [Mask Propagation for Efficient Video Semantic Segmentation](https://mlsanity.com/paper/2310.18954/) (2023)
- [Learning Local and Global Temporal Contexts for Video Semantic Segmentation](https://mlsanity.com/paper/2204.03330/) (2022)
- [AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation](https://mlsanity.com/paper/2306.06842/) (2023)
- [DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation](https://mlsanity.com/paper/2212.11677/) (2022)
- [OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments](https://mlsanity.com/paper/2403.09412/) (2024)
- [Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentation](https://mlsanity.com/paper/2407.11344/) (2024)
- [Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidance](https://mlsanity.com/paper/2102.06685/) (2021)
- [PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation](https://mlsanity.com/paper/2301.00954/) (2023)
- [Self-Regulation for Semantic Segmentation](https://mlsanity.com/paper/2108.09702/) (2021)

## Abstract (arXiv)

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 textitexplicitly modeling the object textitbody and textitedge, 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 textitCityscapes, textitCamVid, textitKIITI and textitBDD 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 (urlhttps://github.com/lxtGH/DecoupleSegNets).