mlsanityData to 7 Oct 2026

Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation

arXiv 2412.14587 ↗First posted 19 Dec 2024cs.CV cs.AI cs.NEcited by 18

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) have a low-power advantage but perform poorly in image segmentation tasks. The reason is that directly converting neural networks with complex architectural designs for segmentation tasks into spiking versions leads to performance degradation and non-convergence. To address this challenge, we first identify the modules in the architecture design that lead to the severe reduction in spike firing, make targeted improvements, and propose Spike2Former architecture. Second, we propose normalized integer spiking neurons to solve the training stability problem of SNNs with complex architectures. We set a new state-of-the-art for SNNs in various semantic segmentation datasets, with a significant improvement of +12.7% mIoU and 5.0 efficiency on ADE20K, +14.3% mIoU and 5.2 efficiency on VOC2012, and +9.1% mIoU and 6.6 efficiency on CityScapes.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 23 of its 38 references that are in the map. First posted on arXiv 19 Dec 2024.

Builds on

23 of 38 references.

References · 23

  1. 2020End-to-End Object Detection with Transformerscited by 7,384
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  7. 2019Searching for MobileNetV3cited by 1,984
  8. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  9. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
  10. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  11. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 263
  12. 2024Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chipscited by 97
11 more
  1. 2021Advancing Spiking Neural Networks towards Deep Residual Learningcited by 76
  2. 2024Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detectioncited by 65
  3. 2024Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Trainingcited by 57
  4. 2021Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentationcited by 54
  5. 2023Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipelinecited by 50
  6. 2020Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networkscited by 46
  7. 2024PEM: Prototype-based Efficient MaskFormer for Image Segmentationcited by 35
  8. 2021A Spiking Neural Network for Image Segmentationcited by 27
  9. 2023You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perceptioncited by 9
  10. 2023Online Transformers with Spiking Neurons for Fast Prosthetic Hand Controlcited by 5
  11. 2024Mixed-Query Transformer: A Unified Image Segmentation Architecturecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 10.

18 papers.

Sort:

By area:

  1. 2025SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networkscited by 11
  2. 2026SpikeTrack: A Spike-driven Framework for Efficient Visual Trackingcited by 4
  3. 2025Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: a Reviewcited by 3
  4. 2025Edge Intelligence with Spiking Neural Networkscited by 2
  5. 2025Exploring the Potentials of Spiking Neural Networks for Image Derainingcited by 2
  6. 2025Efficient Spike-driven Transformer for High-performance Drone-View Geo-Localizationcited by 2
  7. 2025Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmarkcited by 1
  8. 2026Brain-Inspired Multimodal Spiking Neural Network for Image-Text Retrievalcited by 1
  9. 2026A2SG:Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural Networkscited by 1
  10. 2026SpikeVLA: Vision-Language-Action Models with Spiking Neural Networkscited by 1
  11. 2025SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learningcited by 0
  12. 2025Toward Real-Time Surgical Scene Segmentation via a Spike-Driven Video Transformer with Spike-Informed Pretrainingcited by 0
6 more
  1. 2026UIESNN: A Scale-Aware Spiking Network for Underwater Image Enhancementcited by 0
  2. 2026SpikF-GO: Spiking Fourier Graph Operators for Multivariate Time Series Forecastingcited by 0
  3. 2026Robust PnP on a Neuromorphic Processor for Object Pose Estimationcited by 0
  4. 2026Rethinking Attention Locality in Spiking Transformerscited by 0
  5. 2026Spiking Local Interaction and Adaptive Complementary Fusion for Spiking Transformercited by 0
  6. 2026SBMVTrack: Spike-Budgeted Multi-View Learning for Power-Efficient UAV Trackingcited by 0