# Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform

arXiv: https://arxiv.org/abs/1511.03328 · HTML: https://mlsanity.com/paper/1511.03328/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2015.

## Built on by (most cited first, 30 of 46)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [Semantic Diffusion Network for Semantic Segmentation](https://mlsanity.com/paper/2302.02057/) (2023)
- [RoI Tanh-polar Transformer Network for Face Parsing in the Wild](https://mlsanity.com/paper/2102.02717/) (2021)
- [Semantic Segmentation in Art Paintings](https://mlsanity.com/paper/2203.03238/) (2022)
- [A Multi-Branch Hybrid Transformer Networkfor Corneal Endothelial Cell Segmentation](https://mlsanity.com/paper/2106.07557/) (2021)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [A Unified Efficient Pyramid Transformer for Semantic Segmentation](https://mlsanity.com/paper/2107.14209/) (2021)
- [FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2208.14143/) (2022)
- [To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2307.15063/) (2023)
- [HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline](https://mlsanity.com/paper/2103.01849/) (2021)
- [Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundaries](https://mlsanity.com/paper/2110.02833/) (2021)
- [Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2503.21780/) (2025)
- [Boundary Guided Context Aggregation for Semantic Segmentation](https://mlsanity.com/paper/2110.14587/) (2021)
- [An Alternative Practice of Tropical Convolution to Traditional Convolutional Neural Networks](https://mlsanity.com/paper/2103.02096/) (2021)
- [BoundarySqueeze: Image Segmentation as Boundary Squeezing](https://mlsanity.com/paper/2105.11668/) (2021)
- [MoE-SPNet: A Mixture-of-Experts Scene Parsing Network](https://mlsanity.com/paper/1806.07049/) (2018)
- [Edge-competing Pathological Liver Vessel Segmentation with Limited Labels](https://mlsanity.com/paper/2108.00384/) (2021)
- [Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer](https://mlsanity.com/paper/2109.08912/) (2021)
- [Recurrent Feature Propagation and Edge Skip-Connections for Automatic Abdominal Organ Segmentation](https://mlsanity.com/paper/2201.00317/) (2022)
- [Learning to Detect Semantic Boundaries with Image-level Class Labels](https://mlsanity.com/paper/2212.07579/) (2022)
- [The Ikshana Hypothesis of Human Scene Understanding](https://mlsanity.com/paper/2101.10837/) (2021)
- [Visual Boundary Knowledge Translation for Foreground Segmentation](https://mlsanity.com/paper/2108.00379/) (2021)
- [TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency](https://mlsanity.com/paper/2210.05152/) (2022)
- [Edge-aware Plug-and-play Scheme for Semantic Segmentation](https://mlsanity.com/paper/2303.10307/) (2023)
- [OVeNet: Offset Vector Network for Semantic Segmentation](https://mlsanity.com/paper/2303.14516/) (2023)
- [EDCSSM: Edge Detection with Convolutional State Space Model](https://mlsanity.com/paper/2409.01609/) (2024)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) are the backbone of state-of-art semantic image segmentation systems. Recent work has shown that complementing CNNs with fully-connected conditional random fields (CRFs) can significantly enhance their object localization accuracy, yet dense CRF inference is computationally expensive. We propose replacing the fully-connected CRF with domain transform (DT), a modern edge-preserving filtering method in which the amount of smoothing is controlled by a reference edge map. Domain transform filtering is several times faster than dense CRF inference and we show that it yields comparable semantic segmentation results, accurately capturing object boundaries. Importantly, our formulation allows learning the reference edge map from intermediate CNN features instead of using the image gradient magnitude as in standard DT filtering. This produces task-specific edges in an end-to-end trainable system optimizing the target semantic segmentation quality.