# MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs

arXiv: https://arxiv.org/abs/2511.13735 · HTML: https://mlsanity.com/paper/2511.13735/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 64 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [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)
- [Object Detection with Spiking Neural Networks on Automotive Event Data](https://mlsanity.com/paper/2205.04339/) (2022)
- [Advancing Spiking Neural Networks towards Deep Residual Learning](https://mlsanity.com/paper/2112.08954/) (2021)
- [Deep Directly-Trained Spiking Neural Networks for Object Detection](https://mlsanity.com/paper/2307.11411/) (2023)
- [Bi-Directional Cascade Network for Perceptual Edge Detection](https://mlsanity.com/paper/1902.10903/) (2019)
- [Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection](https://mlsanity.com/paper/2407.20708/) (2024)
- [Fast Edge Detection Using Structured Forests](https://mlsanity.com/paper/1406.5549/) (2014)
- [Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN](https://mlsanity.com/paper/2305.19868/) (2023)
- [MQBench: Towards Reproducible and Deployable Model Quantization Benchmark](https://mlsanity.com/paper/2111.03759/) (2021)
- [Dense Extreme Inception Network for Edge Detection](https://mlsanity.com/paper/2112.02250/) (2021)
- [EDTER: Edge Detection with Transformer](https://mlsanity.com/paper/2203.08566/) (2022)
- [SFOD: Spiking Fusion Object Detector](https://mlsanity.com/paper/2403.15192/) (2024)
- [RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses](https://mlsanity.com/paper/2403.01795/) (2024)
- [BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection](https://mlsanity.com/paper/2103.00334/) (2021)
- [Practical Edge Detection via Robust Collaborative Learning](https://mlsanity.com/paper/2308.14084/) (2023)
- [Delving into Crispness: Guided Label Refinement for Crisp Edge Detection](https://mlsanity.com/paper/2306.15172/) (2023)
- [Rapid Salient Object Detection with Difference Convolutional Neural Networks](https://mlsanity.com/paper/2507.01182/) (2025)
- [A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks](https://mlsanity.com/paper/2001.00254/) (2020)
- [Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss](https://mlsanity.com/paper/2102.01301/) (2021)
- [SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networks](https://mlsanity.com/paper/2206.09449/) (2022)
- [Cycle Pixel Difference Network for Crisp Edge Detection](https://mlsanity.com/paper/2409.04272/) (2024)
- [SpikeDet: Better Firing Patterns for Accurate and Energy-Efficient Object Detection with Spiking Neural Networks](https://mlsanity.com/paper/2501.15151/) (2025)

## Abstract (arXiv)

Edge detection with Artificial Neural Networks (ANNs) has achieved remarkable prog-ress but faces two major challenges. First, it requires pre-training on large-scale extra data and complex designs for prior knowledge, leading to high energy consumption. Second, the predicted edges perform poorly in crispness and heavily rely on post-processing. Spiking Neural Networks (SNNs), as third generation neural networks, feature quantization and spike-driven computation mechanisms. They inherently provide a strong prior for edge detection in an energy-efficient manner, while its quantization mechanism helps suppress texture artifact interference around true edges, improving prediction crispness. However, the resulting quantization error inevitably introduces sparse edge discontinuities, compromising further enhancement of crispness. To address these challenges, we propose MS2Edge, the first SNN-based model for edge detection. At its core, we build a novel spiking backbone named MS2ResNet that integrates multi-scale residual learning to recover missing boundary lines and generate crisp edges, while combining I-LIF neurons with Membrane-based Deformed Shortcut (MDS) to mitigate quantization errors. The model is complemented by a Spiking Multi-Scale Upsample Block (SMSUB) for detail reconstruction during upsampling and a Membrane Average Decoding (MAD) method for effective integration of edge maps across multiple time steps. Experimental results demonstrate that MS2Edge outperforms ANN-based methods and achieves state-of-the-art performance on the BSDS500, NYUDv2, BIPED, PLDU, and PLDM datasets without pre-trained backbones, while maintaining ultralow energy consumption and generating crisp edge maps without post-processing.