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

• URL: http://arxiv.org/abs/2511.13735v1
• Date: Wed, 05 Nov 2025 15:56:46 GMT
• Title: MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs
• Authors: Yimeng Fan, Changsong Liu, Mingyang Li, Yuzhou Dai, Yanyan Liu, Wei Zhang,
• Abstract summary: Edge detection with Artificial Neural Networks (ANNs) has achieved remarkable prog-ress but faces two major challenges.<n>It requires pre-training on large-scale extra data and complex designs for prior knowledge, leading to high energy consumption.<n>We build a novel spiking backbone named MS2ResNet that integrates multi-scale residual learning to recover missing boundary lines and generate crisp edges.
• Score: 12.591111929378906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• S$^2$NN: Sub-bit Spiking Neural Networks [53.08060832135342]
  Spiking Neural Networks (SNNs) offer an energy-efficient paradigm for machine intelligence.<n>Despite recent advances in binary SNNs, the storage and computational demands remain substantial for large-scale networks.<n>We propose Sub-bit Spiking Neural Networks (S$2$NNs) that represent weights with less than one bit.
  arXiv  Detail & Related papers  (2025-09-29T04:17:44Z)
• Geminet: Learning the Duality-based Iterative Process for Lightweight Traffic Engineering in Changing Topologies [53.38648279089736]
  Geminet is a lightweight and scalable ML-based TE framework that can handle changing topologies.<n>Its neural network size is only 0.04% to 7% of existing schemes.<n>When trained on large-scale topologies, Geminet consumes under 10 GiB of memory, more than eight times less than the 80-plus GiB required by HARP.
  arXiv  Detail & Related papers  (2025-06-30T09:09:50Z)
• Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representation [2.649410674489787]
  Spiking Neural Networks (SNNs) are highly energy-efficient during inference.<n>Their ability to process event-driven inputs, such as data from dynamic vision sensors (DVS), further enhances their applicability to edge computing tasks.<n>We present the first benchmark for the DVS gesture recognition task using SNNs optimized for the many-core neuromorphic chip SpiNNaker2.
  arXiv  Detail & Related papers  (2025-04-09T10:09:29Z)
• Learning to utilize image second-order derivative information for crisp edge detection [16.152236524867078]
  Edge detection is a fundamental task in computer vision.<n>Recent top-performing edge detection methods tend to generate thick and noisy edge lines.<n>We propose a second-order derivative-based multi-scale contextual enhancement module (SDMCM) to help the model locate true edge pixels accurately.<n>We also construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue.<n>In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for edge detection.
  arXiv  Detail & Related papers  (2024-06-09T13:25:02Z)
• Pursing the Sparse Limitation of Spiking Deep Learning Structures [42.334835610250714]
  Spiking Neural Networks (SNNs) are garnering increased attention for their superior computation and energy efficiency. We introduce an innovative algorithm capable of simultaneously identifying both weight and patch-level winning tickets. We demonstrate that our spiking lottery ticket achieves comparable or superior performance even when the model structure is extremely sparse.
  arXiv  Detail & Related papers  (2023-11-18T17:00:40Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Semi-supervised Impedance Inversion by Bayesian Neural Network Based on 2-d CNN Pre-training [0.966840768820136]
  We improve the semi-supervised learning from two aspects. First, by replacing 1-d convolutional neural network layers in deep learning structure with 2-d CNN layers and 2-d maxpooling layers, the prediction accuracy is improved. Second, prediction uncertainty can also be estimated by embedding the network into a Bayesian inference framework.
  arXiv  Detail & Related papers  (2021-11-20T14:12:05Z)
• Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch [75.69506249886622]
  Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network.
  arXiv  Detail & Related papers  (2021-02-08T05:55:47Z)
• Traditional Method Inspired Deep Neural Network for Edge Detection [7.125116757822889]
  We propose a traditional method inspired framework to produce good edges with minimal complexity. Our TIN2 (Traditional Inspired Network) model has an accuracy higher than the recent BDCN2 (Bi-Directional Cascade Network) but with a smaller model.
  arXiv  Detail & Related papers  (2020-05-28T09:20:37Z)
• Saliency Enhancement using Gradient Domain Edges Merging [65.90255950853674]
  We develop a method to merge the edges with the saliency maps to improve the performance of the saliency. This leads to our proposed saliency enhancement using edges (SEE) with an average improvement of at least 3.4 times higher on the DUT-OMRON dataset. The SEE algorithm is split into 2 parts, SEE-Pre for preprocessing and SEE-Post pour postprocessing.
  arXiv  Detail & Related papers  (2020-02-11T14:04:56Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.