← Back to all news
arXiv Machine Learning By Zhaokun Zhou, Yijie Lu, Kaiwei Che, Wei Fang, Keyu Tian, Qihao Peng, Yuesheng Zhu, Shuicheng Yan, Yonghong Tian, Li Yuan

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

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

Related stories

arXiv AI
Jul 15

Burst Spiking Neural Networks

arXiv:2607. 11914v1 Announce Type: cross Abstract: A central goal of current Spiking Neural Network (SNN) research is to improve their accuracy toward becoming low-power alternatives to Artificial Neural Networks (ANNs).

By Jiahong Zhang, Sijun Shen, Man Yao, Han Xu, Mingqiang Huang, Yonghong Tian, Bo Xu, Guoqi Li
efficiencybenchmarks
More like this →
arXiv AI
Jun 19

Hybrid ANN-SNN Pipeline with Local Plasticity

arXiv:2606. 20151v1 Announce Type: cross Abstract: This work proposes a hybrid ANN-SNN pipeline that effectively leverages the rich embeddings of pretrained artificial neural networks (ANNs) to enable high-performance spiking neural networks (SNNs).

By Denis Larionov, Khairutin Shtanchaev, Mikhail Kiselev, Mikhail Korovin, Ivan Tugoy
ragbenchmarks
More like this →
arXiv AI
2d ago

Contrastive Attention Mitigates Spectral Bias in Spiking Transformers

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.

By Xiaoli Liu, Malu Zhang, Yang Yang
llmscomputer-visionsafety
More like this →
Hugging Face Trending Papers
Jul 22

Current Injection Spiking Neural Network for Infrared and Visible Image Fusion

Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content. While existing methods are largely built on artificial neural networks (ANNs), which densely compute over all activations, spiking neural networks (SNNs) communicate through sparse binary spikes and compute only where and when a spike occurs, offering a route to more energy-efficient fusion.

computer-visionmultimodalbenchmarks
More like this →