# Learning to predict crisp boundaries

arXiv: https://arxiv.org/abs/1807.10097 · HTML: https://mlsanity.com/paper/1807.10097/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2018.

## Built on by (most cited first, 30 of 82)

- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers](https://mlsanity.com/paper/2206.02066/) (2022)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [EDTER: Edge Detection with Transformer](https://mlsanity.com/paper/2203.08566/) (2022)
- [RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth](https://mlsanity.com/paper/2108.00616/) (2021)
- [SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches](https://mlsanity.com/paper/2111.15078/) (2021)
- [AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation](https://mlsanity.com/paper/2306.00977/) (2023)
- [DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection](https://mlsanity.com/paper/2401.02032/) (2024)
- [Tiny and Efficient Model for the Edge Detection Generalization](https://mlsanity.com/paper/2308.06468/) (2023)
- [The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector](https://mlsanity.com/paper/2303.11828/) (2023)
- [3D Segmentation of Humans in Point Clouds with Synthetic Data](https://mlsanity.com/paper/2212.00786/) (2022)
- [DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior](https://mlsanity.com/paper/2303.06834/) (2023)
- [RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses](https://mlsanity.com/paper/2403.01795/) (2024)
- [Lightweight Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2402.00422/) (2024)
- [Practical Edge Detection via Robust Collaborative Learning](https://mlsanity.com/paper/2308.14084/) (2023)
- [Part2Object: Hierarchical Unsupervised 3D Instance Segmentation](https://mlsanity.com/paper/2407.10084/) (2024)
- [Delving into Crispness: Guided Label Refinement for Crisp Edge Detection](https://mlsanity.com/paper/2306.15172/) (2023)
- [Symbol as Points: Panoptic Symbol Spotting via Point-based Representation](https://mlsanity.com/paper/2401.10556/) (2024)
- [CP-loss: Connectivity-preserving Loss for Road Curb Detection in Autonomous Driving with Aerial Images](https://mlsanity.com/paper/2107.11920/) (2021)
- [Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description](https://mlsanity.com/paper/2405.18937/) (2024)
- [Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss](https://mlsanity.com/paper/2102.01301/) (2021)
- [FakeMix Augmentation Improves Transparent Object Detection](https://mlsanity.com/paper/2103.13279/) (2021)
- [IPatch: A Remote Adversarial Patch](https://mlsanity.com/paper/2105.00113/) (2021)
- [Large-Scale Multi-Hypotheses Cell Tracking Using Ultrametric Contours Maps](https://mlsanity.com/paper/2308.04526/) (2023)
- [Internal-External Boundary Attention Fusion for Glass Surface Segmentation](https://mlsanity.com/paper/2307.00212/) (2023)
- [EdgeNAT: Transformer for Efficient Edge Detection](https://mlsanity.com/paper/2408.10527/) (2024)
- [One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning](https://mlsanity.com/paper/2203.09387/) (2022)
- [VIFNet: An End-to-end Visible-Infrared Fusion Network for Image Dehazing](https://mlsanity.com/paper/2404.07790/) (2024)

## Abstract (arXiv)

Recent methods for boundary or edge detection built on Deep Convolutional Neural Networks (CNNs) typically suffer from the issue of predicted edges being thick and need post-processing to obtain crisp boundaries. Highly imbalanced categories of boundary versus background in training data is one of main reasons for the above problem. In this work, the aim is to make CNNs produce sharp boundaries without post-processing. We introduce a novel loss for boundary detection, which is very effective for classifying imbalanced data and allows CNNs to produce crisp boundaries. Moreover, we propose an end-to-end network which adopts the bottom-up/top-down architecture to tackle the task. The proposed network effectively leverages hierarchical features and produces pixel-accurate boundary mask, which is critical to reconstruct the edge map. Our experiments illustrate that directly making crisp prediction not only promotes the visual results of CNNs, but also achieves better results against the state-of-the-art on the BSDS500 dataset (ODS F-score of .815) and the NYU Depth dataset (ODS F-score of .762).