# Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss

arXiv: https://arxiv.org/abs/2102.01301 · HTML: https://mlsanity.com/paper/2102.01301/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 2 Feb 2021.

## Builds on (most cited first, 19 of 19)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Learning Rich Features from RGB-D Images for Object Detection and Segmentation](https://mlsanity.com/paper/1407.5736/) (2014)
- [Learning to predict crisp boundaries](https://mlsanity.com/paper/1807.10097/) (2018)
- [Bi-Directional Cascade Network for Perceptual Edge Detection](https://mlsanity.com/paper/1902.10903/) (2019)
- [Fast Edge Detection Using Structured Forests](https://mlsanity.com/paper/1406.5549/) (2014)
- [Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade](https://mlsanity.com/paper/1704.01344/) (2017)
- [DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection](https://mlsanity.com/paper/1412.1123/) (2014)
- [Pushing the Boundaries of Boundary Detection using Deep Learning](https://mlsanity.com/paper/1511.07386/) (2015)
- [Object Contour Detection with a Fully Convolutional Encoder-Decoder Network](https://mlsanity.com/paper/1603.04530/) (2016)
- [Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction](https://mlsanity.com/paper/1801.00524/) (2018)
- [ N4 -Fields: Neural Network Nearest Neighbor Fields for Image Transforms](https://mlsanity.com/paper/1406.6558/) (2014)
- [Unsupervised Learning of Edges](https://mlsanity.com/paper/1511.04166/) (2015)
- [SemiContour: A Semi-supervised Learning Approach for Contour Detection](https://mlsanity.com/paper/1605.04996/) (2016)
- [Weakly Supervised Object Boundaries](https://mlsanity.com/paper/1511.07803/) (2015)

## Built on by (most cited first, 8 of 8)

- [Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attention](https://mlsanity.com/paper/2104.14374/) (2021)
- [One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning](https://mlsanity.com/paper/2203.09387/) (2022)
- [Cycle Pixel Difference Network for Crisp Edge Detection](https://mlsanity.com/paper/2409.04272/) (2024)
- [Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment](https://mlsanity.com/paper/2210.00413/) (2022)
- [Learning to utilize image second-order derivative information for crisp edge detection](https://mlsanity.com/paper/2406.05779/) (2024)
- [UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network](https://mlsanity.com/paper/2408.04258/) (2024)
- [Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation](https://mlsanity.com/paper/2506.04758/) (2025)
- [MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs](https://mlsanity.com/paper/2511.13735/) (2025)

## Abstract (arXiv)

Significant progress has been made in boundary detection with the help of convolutional neural networks. Recent boundary detection models not only focus on real object boundary detection but also "crisp" boundaries (precisely localized along the object's contour). There are two methods to evaluate crisp boundary performance. One uses more strict tolerance to measure the distance between the ground truth and the detected contour. The other focuses on evaluating the contour map without any postprocessing. In this study, we analyze both methods and conclude that both methods are two aspects of crisp contour evaluation. Accordingly, we propose a novel network named deep refinement network (DRNet) that stacks multiple refinement modules to achieve richer feature representation and a novel loss function, which combines cross-entropy and dice loss through effective adaptive fusion. Experimental results demonstrated that we achieve state-of-the-art performance for several available datasets.