← Back to all news
arXiv Computer Vision By Yimeng Shan, Malu Zhang

Mask IPL: Noise-Free Intrinsic Position Learning via Computation Graph Clipping for Event-Based Spike-Driven Tracking

Read the original on arXiv Computer Vision →

Mask IPL introduces a Computation Graph Clipping technique that removes noise from Intrinsic Position Learning (IPL) in spiking neural networks for event-based tracking. By applying a validity mask to each layer, the method aligns forward and backward propagation with ideal gradients without adding parameters. Experiments show that Mask IPL consistently improves tracking performance on Tiny‑scale and Base‑scale benchmarks such as FE108, FELT, and VisEvent.

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 Computer Vision.

Related stories

arXiv Computer Vision
Sep 23

SBMVTrack: Spike-Budgeted Multi-View Learning for Energy-Efficient UAV Tracking

SBMVTrack is a fully spiking neural network framework designed for energy-efficient UAV visual tracking. It introduces Energy-Weighted Spike Budgeting (EWSB) to constrain spike activity based on computational cost, and Masked Multi-View Target Modeling (MVTM) to enhance target representation by leveraging correlated temporal views. Experiments on multiple benchmarks show that SBMVTrack reduces spike firing rates and theoretical energy consumption while maintaining competitive tracking accuracy.

By Pengzhi Zhong, Jiwei Mo, Haolun Li, Ge Zheng, Jingqi Wang, Xinyi Bo, Shuiwang Li
benchmarks
More like this →
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
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 →