paper-with-me

홈 › Papers

STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks

2025-03-04 · CVPR 2025 1 · Tianqing Zhang, Kairong Yu, Xian Zhong, Hongwei Wang, Qi Xu, Qiang Zhang

Spiking Neural Networks (SNNs) have gained significant attention due to their biological plausibility and energy efficiency, making them promising alternatives to Artificial Neural Networks (ANNs). However, the performance gap between SNNs and ANNs remains a substantial challenge hindering the widespread adoption of SNNs. In this paper, we propose a Spatial-Temporal Attention Aggregator SNN (STAA-SNN) framework, which dynamically focuses on and captures both spatial and temporal dependencies. First, we introduce a spike-driven self-attention mechanism specifically designed for SNNs. Additionally, we pioneeringly incorporate position encoding to integrate latent temporal relationships into the incoming features. For spatial-temporal information aggregation, we employ step attention to selectively amplify relevant features at different steps. Finally, we implement a time-step random dropout strategy to avoid local optima. As a result, STAA-SNN effectively captures both spatial and temporal dependencies, enabling the model to analyze complex patterns and make accurate predictions. The framework demonstrates exceptional performance across diverse datasets and exhibits strong generalization capabilities. Notably, STAA-SNN achieves state-of-the-art results on neuromorphic datasets CIFAR10-DVS, with remarkable performances of 97.14%, 82.05% and 70.40% on the static datasets CIFAR-10, CIFAR-100 and ImageNet, respectively. Furthermore, our model exhibits improved performance ranging from 0.33\% to 2.80\% with fewer time steps. The code for the model is available on GitHub.

📄 PDF Abstract BibTeX arXiv:2503.02689

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
SNN Spiking Neural Networks (SNNs) are a class of artificial neural networks inspired by the structure and functioning of the brain's neural networks. Unlike traditional…

Similar Papers 제목 키워드 기반

STAA: Spatio-Temporal Attention Attribution for Real-Time Interpreting Transformer-based Video Models

2024-11-01 · Zerui Wang, Yan Liu

Transformer-based models have achieved state-of-the-art performance in various computer vision tasks, including image and video analysis. However, Transformer's complex architecture and black-box nature pose challenges f…

Action RecognitionFeature Importance

Spatial-Temporal Adaptive Graph Convolution with Attention Network for Traffic Forecasting

2022-06-07 · Chen Weikang, Li Yawen, Xue Zhe, LI ANG 외

Traffic forecasting is one canonical example of spatial-temporal learning task in Intelligent Traffic System. Existing approaches capture spatial dependency with a pre-determined matrix in graph convolution neural operat…

Graph AttentionTime SeriesTime Series Analysis

Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning

2025-01-17 · Xu Chu, Hanlin Xue, Bingce Wang, Xiaoyang Liu 외

Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most methods assume temporal locality, meaning that recent edges are more influential than earlier edges. However, for temporal changes in ed…

Graph LearningLink PredictionNode Classification

STPFormer: A State-of-the-Art Pattern-Aware Spatio-Temporal Transformer for Traffic Forecasting

2025-08-19 · Jiayu Fang, Zhiqi Shao, S T Boris Choy, Junbin Gao arxiv

Spatio-temporal traffic forecasting is challenging due to complex temporal patterns, dynamic spatial structures, and diverse input formats. Although Transformer-based models offer strong global modeling, they often strug…

Representation LearningGraph Matching

Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks

2024-01-08 · NeurIPS 2023 11 · Qi Xu, Yuyuan Gao, Jiangrong Shen, Yaxin Li 외

Spiking neural networks (SNNs) serve as one type of efficient model to process spatio-temporal patterns in time series, such as the Address-Event Representation data collected from Dynamic Vision Sensor (DVS). Although c…

Time Series