arXiv:2608. 19238v1 Announce Type: cross Abstract: Spiking Transformers model token interactions primarily through spiking self-attention (SSA).
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.
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.
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.
arXiv:2609.37047v1 Announce Type: cross Abstract: We propose a new spiking neural network (SNN) design to process static images and event streams using time-to-first-spike (TTFS) latencies. Our key r...
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.
MSGAT introduces a Multi-head Spiking Graph Attention Network that models structural relationships for image-text retrieval using spike-driven graph reasoning. It employs dynamic attention heads to capture complementary relational patterns and a two-branch multi-granularity fusion framework. The proposed Sim-Fuse strategy aligns coarse- and fine-grained matching relations in similarity space, avoiding interference between sparse spike representations and continuous global features, achieving state‑of‑the‑art performance on Flickr30K and MSCOCO with significant energy savings.
arXiv:2604. 08894v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs).