mlsanityData to 7 Oct 2026

TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks

arXiv 2206.10177 ↗First posted 21 Jun 2022cs.CV cs.AIcited by 33

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) are attracting widespread interest due to their biological plausibility, energy efficiency, and powerful spatio-temporal information representation ability. Given the critical role of attention mechanisms in enhancing neural network performance, the integration of SNNs and attention mechanisms exhibits potential to deliver energy-efficient and high-performance computing paradigms. We present a novel Temporal-Channel Joint Attention mechanism for SNNs, referred to as TCJA-SNN. The proposed TCJA-SNN framework can effectively assess the significance of spike sequence from both spatial and temporal dimensions. More specifically, our essential technical contribution lies on: 1) We employ the squeeze operation to compress the spike stream into an average matrix. Then, we leverage two local attention mechanisms based on efficient 1D convolutions to facilitate comprehensive feature extraction at the temporal and channel levels independently. 2) We introduce the Cross Convolutional Fusion (CCF) layer as a novel approach to model the inter-dependencies between the temporal and channel scopes. This layer breaks the independence of these two dimensions and enables the interaction between features. Experimental results demonstrate that the proposed TCJA-SNN outperforms SOTA by up to 15.7% accuracy on standard static and neuromorphic datasets, including Fashion-MNIST, CIFAR10-DVS, N-Caltech 101, and DVS128 Gesture. Furthermore, we apply the TCJA-SNN framework to image generation tasks by leveraging a variation autoencoder. To the best of our knowledge, this study is the first instance where the SNN-attention mechanism has been employed for image classification and generation tasks. Notably, our approach has achieved SOTA performance in both domains, establishing a significant advancement in the field. Codes are available at https://github.com/ridgerchu/TCJA.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 33 of its 86 references that are in the map. First posted on arXiv 21 Jun 2022.

Builds on

33 of 86 references.

References · 33

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  7. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  8. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
  9. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  10. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  11. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
  12. 2021Deep Residual Learning in Spiking Neural Networkscited by 326
21 more
  1. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 308
  2. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  3. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
  4. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
  5. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  6. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 215
  7. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 203
  8. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 192
  9. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 179
  10. 2021Temporal-wise Attention Spiking Neural Networks for Event Streams Classificationcited by 106
  11. 2022Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representationcited by 89
  12. 2020LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processingcited by 56
  13. 2022Neuromorphic Data Augmentation for Training Spiking Neural Networkscited by 52
  14. 2020Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networkscited by 46
  15. 2017DART: Distribution Aware Retinal Transform for Event-based Camerascited by 39
  16. 2019Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networkscited by 32
  17. 2018Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networkscited by 30
  18. 2021Fully Spiking Variational Autoencodercited by 22
  19. 2022Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimizationcited by 13
  20. 2021Advancing Deep Residual Learning by Solving the Crux of Degradation in Spiking Neural Networkscited by 3
  21. 2022SIT: A Bionic and Non-Linear Neuron for Spiking Neural Networkcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 7; 2025: 10; 2026: 4.

33 papers.

Sort:

By area:

  1. 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 163
  2. 2023SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networkscited by 82
  3. 2023Direct Learning-Based Deep Spiking Neural Networks: A Reviewcited by 31
  4. 2025Spiking Vision Transformer with Saccadic Attentioncited by 21
  5. 2023Inherent Redundancy in Spiking Neural Networkscited by 13
  6. 2024Autonomous Driving with Spiking Neural Networkscited by 12
  7. 2025Rethinking Spiking Neural Networks from an Ensemble Learning Perspectivecited by 12
  8. 2024TIM: An Efficient Temporal Interaction Module for Spiking Transformercited by 11
  9. 2025STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networkscited by 11
  10. 2023Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Futurecited by 10
  11. 2023Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagationcited by 8
  12. 2023Tensor Decomposition Based Attention Module for Spiking Neural Networkscited by 8
21 more
  1. 2022A Spatial-channel-temporal-fused Attention for Spiking Neural Networkscited by 7
  2. 2024Advancing Spiking Neural Networks towards Multiscale Spatiotemporal Interaction Learningcited by 7
  3. 2025TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecastingcited by 6
  4. 2024Degree-Conscious Spiking Graph for Cross-Domain Adaptationcited by 5
  5. 2025Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networkscited by 5
  6. 2024Global-Local Convolution with Spiking Neural Networks for Energy-efficient Keyword Spottingcited by 4
  7. 2023Exploiting High Performance Spiking Neural Networks with Efficient Spiking Patternscited by 3
  8. 2023RN-Net: Reservoir Nodes-Enabled Neuromorphic Vision Sensing Networkcited by 3
  9. 2024ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognitioncited by 3
  10. 2023SynA-ResNet: Spike-driven ResNet Achieved through OR Residual Connectioncited by 2
  11. 2024EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Visioncited by 2
  12. 2025Memory-Free and Parallel Computation for Quantized Spiking Neural Networkscited by 2
  13. 2025Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendlinesscited by 2
  14. 2025Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domaincited by 2
  15. 2025CS3D: An Efficient Facial Expression Recognition via Event Visioncited by 2
  16. 2023The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural Networkscited by 1
  17. 2026Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Modelscited by 1
  18. 2026Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradientscited by 1
  19. 2025DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networkscited by 0
  20. 2026Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networkscited by 0
  21. 2026Collapse or Preserve: Data-Dependent Temporal Aggregation for Spiking Neural Network Accelerationcited by 0