# One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning

arXiv: https://arxiv.org/abs/2203.09387 · HTML: https://mlsanity.com/paper/2203.09387/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 52 references that are in the map.
- First posted on arXiv 17 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Richer Convolutional Features for Edge Detection](https://mlsanity.com/paper/1612.02103/) (2016)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [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)
- [Object Contour Detection with a Fully Convolutional Encoder-Decoder Network](https://mlsanity.com/paper/1603.04530/) (2016)
- [Unmixing Convolutional Features for Crisp Edge Detection](https://mlsanity.com/paper/2011.09808/) (2020)
- [Convolutional Oriented Boundaries](https://mlsanity.com/paper/1608.02755/) (2016)
- [Deep Crisp Boundaries: From Boundaries to Higher-level Tasks](https://mlsanity.com/paper/1801.02439/) (2018)
- [ N4 -Fields: Neural Network Nearest Neighbor Fields for Image Transforms](https://mlsanity.com/paper/1406.6558/) (2014)
- [Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss](https://mlsanity.com/paper/2102.01301/) (2021)

## Built on by (most cited first, 5 of 5)

- [Boosting Edge Detection with Pixel-wise Feature Selection: The Extractor-Selector Paradigm](https://mlsanity.com/paper/2501.02534/) (2025)
- [A Comprehensive Study for Edge Detection: Ideal-Prior Guidance Learning, High-Precision Architecture, and Better Distinguishability Evaluation Benchmark](https://mlsanity.com/paper/2407.19992/) (2024)
- [Symmetrization Weighted Binary Cross-Entropy: Modeling Perceptual Asymmetry for Human-Consistent Neural Edge Detection](https://mlsanity.com/paper/2501.13365/) (2025)
- [Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detection](https://mlsanity.com/paper/2506.12460/) (2025)
- [Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detection](https://mlsanity.com/paper/2507.06569/) (2025)

## Abstract (arXiv)

Edge detection, a basic task in the field of computer vision, is an important preprocessing operation for the recognition and understanding of a visual scene. In conventional models, the edge image generated is ambiguous, and the edge lines are also very thick, which typically necessitates the use of non-maximum suppression (NMS) and morphological thinning operations to generate clear and thin edge images. In this paper, we aim to propose a one-stage neural network model that can generate high-quality edge images without postprocessing. The proposed model adopts a classic encoder-decoder framework in which a pre-trained neural model is used as the encoder and a multi-feature-fusion mechanism that merges the features of each level with each other functions as a learnable decoder. Further, we propose a new loss function that addresses the pixel-level imbalance in the edge image by suppressing the false positive (FP) edge information near the true positive (TP) edge and the false negative (FN) non-edge. The results of experiments conducted on several benchmark datasets indicate that the proposed method achieves state-of-the-art results without using NMS and morphological thinning operations.