← Back to all news
arXiv AI By Xiaoli Liu, Malu Zhang, Yang Yang

Contrastive Attention Mitigates Spectral Bias in Spiking Transformers

Read the original on arXiv AI →

The paper introduces Spiking Contrastive Attention (SCA), a module designed to reduce spectral bias in Spiking Transformers by enhancing high‑frequency information. It demonstrates that spiking neurons and spiking self‑attention act as low‑pass filters, leading to loss of high‑frequency components. Experiments show that SCA improves performance across image classification, semantic segmentation, and event‑based tracking while maintaining lower complexity than the original spiking self‑attention.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Aug 19

Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket

Spikformer V2 introduces a Spiking Self‑Attention (SSA) mechanism that removes softmax and uses spike‑based Query, Key, and Value to capture sparse visual features efficiently. It also adds a Spiking Convolutional Stem (SCS) and employs self‑supervised learning (masking and reconstruction) to pre‑train the model before fine‑tuning on ImageNet. The result is the first spiking neural network to surpass 80 % accuracy on ImageNet, achieving 81.10 % with a 172 M‑parameter, 16‑layer model in just one time step.

By Zhaokun Zhou, Yijie Lu, Kaiwei Che, Wei Fang, Keyu Tian, Qihao Peng, Yuesheng Zhu, Shuicheng Yan, Yonghong Tian, Li Yuan
llmscomputer-vision
More like this →
arXiv AI
Aug 17

SAGE: Surrogate-gradient Adaptation via Attention-Guided Entropy for Spiking Transformers

arXiv:2608. 13702v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep neural networks by exploiting sparse event-driven computation, but their training remains challenging because the non-differentiable spike function requires surrogate gradients whose fixed shape may be suboptimal across layers and training stages.

By Kiran Nair, Rodrigue Rizk, KC Santosh
llms
More like this →