# DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection

arXiv: https://arxiv.org/abs/1412.1123 · HTML: https://mlsanity.com/paper/1412.1123/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2014.

## Built on by (most cited first, 30 of 50)

- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Graph Stacked Hourglass Networks for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.16385/) (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)
- [The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector](https://mlsanity.com/paper/2303.11828/) (2023)
- [OmniControlNet: Dual-stage Integration for Conditional Image Generation](https://mlsanity.com/paper/2406.05871/) (2024)
- [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)
- [Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels](https://mlsanity.com/paper/2110.15606/) (2021)
- [Practical Edge Detection via Robust Collaborative Learning](https://mlsanity.com/paper/2308.14084/) (2023)
- [AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios](https://mlsanity.com/paper/2410.14379/) (2024)
- [Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction](https://mlsanity.com/paper/2101.02843/) (2021)
- [Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss](https://mlsanity.com/paper/2102.01301/) (2021)
- [Learning Deep Morphological Networks with Neural Architecture Search](https://mlsanity.com/paper/2106.07714/) (2021)
- [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)
- [Generative Edge Detection with Stable Diffusion](https://mlsanity.com/paper/2410.03080/) (2024)
- [Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery](https://mlsanity.com/paper/2504.02534/) (2025)
- [Cycle Pixel Difference Network for Crisp Edge Detection](https://mlsanity.com/paper/2409.04272/) (2024)
- [Boosting Edge Detection with Pixel-wise Feature Selection: The Extractor-Selector Paradigm](https://mlsanity.com/paper/2501.02534/) (2025)
- [TextureSAM: Towards a Texture Aware Foundation Model for Segmentation](https://mlsanity.com/paper/2505.16540/) (2025)
- [Edge Prior Augmented Networks for Motion Deblurring on Naturally Blurry Images](https://mlsanity.com/paper/2109.08915/) (2021)
- [STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization](https://mlsanity.com/paper/2201.05121/) (2022)
- [Zero Pixel Directional Boundary by Vector Transform](https://mlsanity.com/paper/2203.08795/) (2022)
- [SketchCleanNet -- A deep learning approach to the enhancement and correction of query sketches for a 3D CAD model retrieval system](https://mlsanity.com/paper/2207.00732/) (2022)
- [DifferSketching: How Differently Do People Sketch 3D Objects?](https://mlsanity.com/paper/2209.08791/) (2022)
- [Learning to Detect Semantic Boundaries with Image-level Class Labels](https://mlsanity.com/paper/2212.07579/) (2022)
- [Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model Estimation](https://mlsanity.com/paper/2308.13779/) (2023)
- [Multiresolution local smoothness detection in non-uniformly sampled multivariate signals](https://mlsanity.com/paper/2507.13480/) (2025)
- [Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation](https://mlsanity.com/paper/2309.15726/) (2023)

## Abstract (arXiv)

Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a higher-level task such as object detection. However, we claim that recognizing objects and predicting contours are two mutually related tasks. Contrary to traditional approaches, we show that we can invert the commonly established pipeline: instead of detecting contours with low-level cues for a higher-level recognition task, we exploit object-related features as high-level cues for contour detection. We achieve this goal by means of a multi-scale deep network that consists of five convolutional layers and a bifurcated fully-connected sub-network. The section from the input layer to the fifth convolutional layer is fixed and directly lifted from a pre-trained network optimized over a large-scale object classification task. This section of the network is applied to four different scales of the image input. These four parallel and identical streams are then attached to a bifurcated sub-network consisting of two independently-trained branches. One branch learns to predict the contour likelihood (with a classification objective) whereas the other branch is trained to learn the fraction of human labelers agreeing about the contour presence at a given point (with a regression criterion). We show that without any feature engineering our multi-scale deep learning approach achieves state-of-the-art results in contour detection.