# Object Contour and Edge Detection with RefineContourNet

arXiv: https://arxiv.org/abs/1904.13353 · HTML: https://mlsanity.com/paper/1904.13353/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2019.

## Built on by (most cited first, 12 of 12)

- [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)
- [RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses](https://mlsanity.com/paper/2403.01795/) (2024)
- [Learning Deep Morphological Networks with Neural Architecture Search](https://mlsanity.com/paper/2106.07714/) (2021)
- [Measuring uncertainty in human visual segmentation](https://mlsanity.com/paper/2301.07807/) (2023)
- [MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision](https://mlsanity.com/paper/2602.20689/) (2026)
- [ECT: Fine-grained Edge Detection with Learned Cause Tokens](https://mlsanity.com/paper/2308.03092/) (2023)
- [Msmsfnet: a multi-stream and multi-scale fusion net for edge detection](https://mlsanity.com/paper/2404.04856/) (2024)
- [UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network](https://mlsanity.com/paper/2408.04258/) (2024)
- [Training-free Quantum-Inspired Image Edge Extraction Method](https://mlsanity.com/paper/2501.18929/) (2025)
- [Walk the Lines 2: Contour Tracking for Detailed Segmentation](https://mlsanity.com/paper/2511.05210/) (2025)
- [Contour Refinement using Discrete Diffusion in Low Data Regime](https://mlsanity.com/paper/2602.05880/) (2026)

## Abstract (arXiv)

A ResNet-based multi-path refinement CNN is used for object contour detection. For this task, we prioritise the effective utilization of the high-level abstraction capability of a ResNet, which leads to state-of-the-art results for edge detection. Keeping our focus in mind, we fuse the high, mid and low-level features in that specific order, which differs from many other approaches. It uses the tensor with the highest-levelled features as the starting point to combine it layer-by-layer with features of a lower abstraction level until it reaches the lowest level. We train this network on a modified PASCAL VOC 2012 dataset for object contour detection and evaluate on a refined PASCAL-val dataset reaching an excellent performance and an Optimal Dataset Scale (ODS) of 0.752. Furthermore, by fine-training on the BSDS500 dataset we reach state-of-the-art results for edge-detection with an ODS of 0.824.