SAFformer:Improving Spiking Transformer via Active Predictive Filtering

• URL: http://arxiv.org/abs/2605.08270v1
• Date: Fri, 08 May 2026 03:17:52 GMT
• Title: SAFformer:Improving Spiking Transformer via Active Predictive Filtering
• Abstract summary: Spiking Neural Networks (SNNs) offer notable advantages in biological plausibility and energy efficiency.<n>We propose SAFformer, a novel Spiking Transformer architecture based on an active predictive filtering paradigm.<n>Experiments show that SAFformer establishes new state-of-the-art performance on CIFAR-10/100 and CIFAR10-DVS.
• Score: 6.339831937684366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spiking Neural Networks (SNNs) offer notable advantages in biological plausibility and energy efficiency, making them promising candidates for building low-power Transformers. However, existing Spiking Transformers largely adhere to a passive reactive paradigm, which struggles to focus on task-relevant information and incurs substantial computational overhead when processing redundant visual data. To overcome this fundamental yet underexplored limitation, we propose SAFformer, a novel Spiking Transformer architecture based on an active predictive filtering paradigm. Inspired by the brain's predictive coding mechanism, SAFformer actively suppresses predictable signals and focuses on salient visual features. Extensive experiments show that SAFformer establishes new state-of-the-art performance on CIFAR-10/100 and CIFAR10-DVS. Remarkably, on ImageNet-1K, it achieves 80.50% Top-1 accuracy with only 26.58M parameters and an energy consumption of 5.88 mJ, demonstrating an exceptional balance between accuracy and efficiency.

Related papers

• Foveation-Guided Dynamic Token Selection for Robust and Efficient Vision Transformers [33.36466188187489]
  Foveated Dynamic Transformer (FDT) integrates foveation-guided dynamic token-selection architecture into vision transformer framework.<n>FDT exhibits strong resilience to various types of noise and adversarial attacks, despite not being explicitly trained for such challenges.<n>These attributes position as an HVS-inspired step toward artificial neural networks that combine adaptive computation with improved resilience.
  arXiv  Detail & Related papers  (2026-07-10T14:53:16Z)
• DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images [50.96240625673857]
  DroneFINE is a novel PEFT paradigm comprising two domain-aware complementary modules tailored for VLM-based drone image detectors.<n>DroneFINE significantly outperforms existing PEFT methods and achieves performance comparable to full fine-tuning.
  arXiv  Detail & Related papers  (2026-07-01T02:27:40Z)
• Neural Dynamics Self-Attention for Spiking Transformers [59.57278823240336]
  Spiking Neural Networks (SNNs) with Transformer architectures offer a promising pathway to balance energy efficiency and performance.<n>Existing Spiking Transformers face two critical challenges: (i) a substantial performance gap compared to their Artificial Neural Networks (ANNs) counterparts and (ii) high memory overhead during inference.<n>We propose LRF-Dyn, which uses spiking neurons with localized receptive fields to compute attention while reducing memory requirements.
  arXiv  Detail & Related papers  (2026-03-09T12:23:37Z)
• Spark Transformer: Reactivating Sparsity in FFN and Attention [53.221448818147024]
  We introduce Spark Transformer, a novel architecture that achieves a high level of activation sparsity in both FFN and the attention mechanism.<n>This sparsity translates to a 2.5x reduction in FLOPs, leading to decoding wall-time speedups of up to 1.79x on CPU and 1.40x on GPU.
  arXiv  Detail & Related papers  (2025-06-07T03:51:13Z)
• TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularization [3.693610259830098]
  Adrial transferability remains a critical challenge in evaluating the robustness of deep neural networks.<n>We introduce textbfTESSER -- a novel adversarial attack framework that enhances transferability via two key strategies.<n>Experiments on ImageNet across 12 diverse architectures demonstrate that TESSER achieves +10.9% higher attack succes rate (ASR) on CNNs and +7.2% on ViTs.
  arXiv  Detail & Related papers  (2025-05-26T07:30:00Z)
• Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer [15.93436166506258]
  Spiking Neural Networks have emerged as a promising energy-efficient alternative to traditional Artificial Neural Networks.<n>This paper introduces Accurate Addition-Only Spiking Self-Attention (A$2$OS$2$A)
  arXiv  Detail & Related papers  (2025-02-28T22:23:29Z)
• A Transformer-in-Transformer Network Utilizing Knowledge Distillation for Image Recognition [0.8196125054032961]
  We propose an inner-outer transformer-based architecture, which gives attention to the global and local aspects of the image.<n>Our approach enhances learning efficiency and effectiveness.<n>Remarkably, the proposed Transformer-in-Transformer Network (TITN) model achieves impressive milestones across various datasets.
  arXiv  Detail & Related papers  (2025-02-24T00:41:46Z)
• Video Prediction Transformers without Recurrence or Convolution [65.93130697098658]
  We propose PredFormer, a framework entirely based on Gated Transformers.<n>We provide a comprehensive analysis of 3D Attention in the context of video prediction.<n>The significant improvements in both accuracy and efficiency highlight the potential of PredFormer.
  arXiv  Detail & Related papers  (2024-10-07T03:52:06Z)
• External Prompt Features Enhanced Parameter-efficient Fine-tuning for Salient Object Detection [6.5971464769307495]
  Salient object detection (SOD) aims at finding the most salient objects in images and outputs pixel-level binary masks. Transformer-based methods achieve promising performance due to their global semantic understanding. We propose a novel parameter-efficient fine-tuning method aimed at reducing the number of training parameters.
  arXiv  Detail & Related papers  (2024-04-23T13:15:07Z)
• MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection [54.545054873239295]
  Deepfakes have recently raised significant trust issues and security concerns among the public.<n>ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance.<n>This work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach.
  arXiv  Detail & Related papers  (2024-04-12T13:02:08Z)
• Spikformer: When Spiking Neural Network Meets Transformer [102.91330530210037]
  We consider two biologically plausible structures, the Spiking Neural Network (SNN) and the self-attention mechanism. We propose a novel Spiking Self Attention (SSA) as well as a powerful framework, named Spiking Transformer (Spikformer)
  arXiv  Detail & Related papers  (2022-09-29T14:16:49Z)
• MViT: Mask Vision Transformer for Facial Expression Recognition in the wild [77.44854719772702]
  Facial Expression Recognition (FER) in the wild is an extremely challenging task in computer vision. In this work, we first propose a novel pure transformer-based mask vision transformer (MViT) for FER in the wild. Our MViT outperforms state-of-the-art methods on RAF-DB with 88.62%, FERPlus with 89.22%, and AffectNet-7 with 64.57%, respectively, and achieves a comparable result on AffectNet-8 with 61.40%.
  arXiv  Detail & Related papers  (2021-06-08T16:58:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.