mlsanityData to 14 Oct 2026

Cross Knowledge Distillation between Artificial and Spiking Neural Networks

arXiv 2507.09269 ↗First posted 12 Jul 2025cs.CV cs.AIcited by 4

On the map: Knowledge distillation → Distillation for spiking neural networks

Abstract (arXiv)

Recently, Spiking Neural Networks (SNNs) have demonstrated rich potential in computer vision domain due to their high biological plausibility, event-driven characteristic and energy-saving efficiency. Still, limited annotated event-based datasets and immature SNN architectures result in their performance inferior to that of Artificial Neural Networks (ANNs). To enhance the performance of SNNs on their optimal data format, DVS data, we explore using RGB data and well-performing ANNs to implement knowledge distillation. In this case, solving cross-modality and cross-architecture challenges is necessary. In this paper, we propose cross knowledge distillation (CKD), which not only leverages semantic similarity and sliding replacement to mitigate the cross-modality challenge, but also uses an indirect phased knowledge distillation to mitigate the cross-architecture challenge. We validated our method on main-stream neuromorphic datasets, including N-Caltech101 and CEP-DVS. The experimental results show that our method outperforms current State-of-the-Art methods. The code will be available at https://github.com/ShawnYE618/CKD

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Distillation for spiking neural networks, one of 12 directions in Knowledge distillation. Builds on 19 of its 35 references that are in the map. First posted on arXiv 12 Jul 2025.

Builds on

19 of 35 references.

References · 19

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  3. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 314
  4. 2018Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotioncited by 307
  5. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 218
  6. 2022Knowledge Distillation from A Stronger Teachercited by 208
  7. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 198
  8. 2022Neuromorphic Data Augmentation for Training Spiking Neural Networkscited by 52
  9. 2020SpinalNet: Deep Neural Network with Gradual Inputcited by 40
  10. 2023Ternary Spike: Learning Ternary Spikes for Spiking Neural Networkscited by 38
  11. 2022BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulationcited by 33
  12. 2020Distilling Spikes: Knowledge Distillation in Spiking Neural Networkscited by 27
7 more
  1. 2025UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networkscited by 19
  2. 2022An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connectionscited by 13
  3. 2023LaSNN: Layer-wise ANN-to-SNN Distillation for Effective and Efficient Training in Deep Spiking Neural Networkscited by 12
  4. 2023Improving Stability and Performance of Spiking Neural Networks through Enhancing Temporal Consistencycited by 10
  5. 2023An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domaincited by 9
  6. 2023Reduction of Class Activation Uncertainty with Background Informationcited by 3
  7. 2024ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognitioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domaincited by 2
  2. 2025Sparse by Rule: Probability-Based N:M Pruning for Spiking Neural Networkscited by 1
  3. 2026STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillationcited by 0
  4. 2026ENCORE: Event-Assisted Complementary Motion Refinement for Learned Video Compressioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Energy-efficient Knowledge Distillation for Spiking Neural Networks
  2. 2025A Closer Look at Knowledge Distillation in Spiking Neural Network Training
  3. 2023Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation
  4. 2025Head-Tail-Aware KL Divergence in Knowledge Distillation for Spiking Neural Networks
  5. 2025Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks
  6. 2024Towards Low-latency Event-based Visual Recognition with Hybrid Step-wise Distillation Spiking Neural Networks
  7. 2024On Reducing Activity with Distillation and Regularization for Energy Efficient Spiking Neural Networks
  8. 2025Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment