# Semantic Segmentation with Boundary Neural Fields

arXiv: https://arxiv.org/abs/1511.02674 · HTML: https://mlsanity.com/paper/1511.02674/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2015.

## Built on by (most cited first, 30 of 37)

- [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)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation](https://mlsanity.com/paper/2107.11264/) (2021)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation](https://mlsanity.com/paper/2403.16605/) (2024)
- [Active Boundary Loss for Semantic Segmentation](https://mlsanity.com/paper/2102.02696/) (2021)
- [Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds](https://mlsanity.com/paper/2101.02381/) (2021)
- [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)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [Lightweight Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2402.00422/) (2024)
- [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)
- [Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation](https://mlsanity.com/paper/2107.09858/) (2021)
- [Delving into Crispness: Guided Label Refinement for Crisp Edge Detection](https://mlsanity.com/paper/2306.15172/) (2023)
- [MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment](https://mlsanity.com/paper/2407.21654/) (2024)
- [SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning](https://mlsanity.com/paper/2309.17083/) (2023)
- [IDRNet: Intervention-Driven Relation Network for Semantic Segmentation](https://mlsanity.com/paper/2310.10755/) (2023)
- [Boundary Guided Context Aggregation for Semantic Segmentation](https://mlsanity.com/paper/2110.14587/) (2021)
- [BoundarySqueeze: Image Segmentation as Boundary Squeezing](https://mlsanity.com/paper/2105.11668/) (2021)
- [Understanding Dark Scenes by Contrasting Multi-Modal Observations](https://mlsanity.com/paper/2308.12320/) (2023)
- [Dynamic High-frequency Convolution for Infrared Small Target Detection](https://mlsanity.com/paper/2602.02969/) (2026)
- [Edge-competing Pathological Liver Vessel Segmentation with Limited Labels](https://mlsanity.com/paper/2108.00384/) (2021)
- [Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2212.12402/) (2022)
- [SegT: A Novel Separated Edge-guidance Transformer Network for Polyp Segmentation](https://mlsanity.com/paper/2306.10773/) (2023)
- [Learning to Detect Semantic Boundaries with Image-level Class Labels](https://mlsanity.com/paper/2212.07579/) (2022)
- [Visual Boundary Knowledge Translation for Foreground Segmentation](https://mlsanity.com/paper/2108.00379/) (2021)

## Abstract (arXiv)

The state-of-the-art in semantic segmentation is currently represented by fully convolutional networks (FCNs). However, FCNs use large receptive fields and many pooling layers, both of which cause blurring and low spatial resolution in the deep layers. As a result FCNs tend to produce segmentations that are poorly localized around object boundaries. Prior work has attempted to address this issue in post-processing steps, for example using a color-based CRF on top of the FCN predictions. However, these approaches require additional parameters and low-level features that are difficult to tune and integrate into the original network architecture. Additionally, most CRFs use color-based pixel affinities, which are not well suited for semantic segmentation and lead to spatially disjoint predictions. To overcome these problems, we introduce a Boundary Neural Field (BNF), which is a global energy model integrating FCN predictions with boundary cues. The boundary information is used to enhance semantic segment coherence and to improve object localization. Specifically, we first show that the convolutional filters of semantic FCNs provide good features for boundary detection. We then employ the predicted boundaries to define pairwise potentials in our energy. Finally, we show that our energy decomposes semantic segmentation into multiple binary problems, which can be relaxed for efficient global optimization. We report extensive experiments demonstrating that minimization of our global boundary-based energy yields results superior to prior globalization methods, both quantitatively as well as qualitatively.