EventRPG: Event Data Augmentation with Relevance Propagation Guidance

2024-03-14 · Mingyuan Sun, Donghao Zhang, ZongYuan Ge, Jiaxu Wang, Jia Li, Zheng Fang, Renjing Xu

Event camera, a novel bio-inspired vision sensor, has drawn a lot of attention for its low latency, low power consumption, and high dynamic range. Currently, overfitting remains a critical problem in event-based classification tasks for Spiking Neural Network (SNN) due to its relatively weak spatial representation capability. Data augmentation is a simple but efficient method to alleviate overfitting and improve the generalization ability of neural networks, and saliency-based augmentation methods are proven to be effective in the image processing field. However, there is no approach available for extracting saliency maps from SNNs. Therefore, for the first time, we present Spiking Layer-Time-wise Relevance Propagation rule (SLTRP) and Spiking Layer-wise Relevance Propagation rule (SLRP) in order for SNN to generate stable and accurate CAMs and saliency maps. Based on this, we propose EventRPG, which leverages relevance propagation on the spiking neural network for more efficient augmentation. Our proposed method has been evaluated on several SNN structures, achieving state-of-the-art performance in object recognition tasks including N-Caltech101, CIFAR10-DVS, with accuracies of 85.62% and 85.55%, as well as action recognition task SL-Animals with an accuracy of 91.59%. Our code is available at https://github.com/myuansun/EventRPG.

📄 PDF Abstract BibTeX arXiv:2403.09274

Code (1)

myuansun/eventrpg 공식 구현 pytorch

Tasks

Action Recognition Data Augmentation Object Recognition

Methods 이 논문이 사용한 방법론

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…

Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation

2020-02-24 · Mathilde Guillemot, Catherine Heusele, Rodolphe Korichi, Sylvianne Schnebert 외

The lack of transparency of neural networks stays a major break for their use. The Layerwise Relevance Propagation technique builds heat-maps representing the relevance of each input in the model s decision. The relevanc…

Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation

2024-04-22 · Paulo Yanez Sarmiento, Simon Witzke, Nadja Klein, Bernhard Y. Renard

Explainability is a key component in many applications involving deep neural networks (DNNs). However, current explanation methods for DNNs commonly leave it to the human observer to distinguish relevant explanations fro…

Explainable Deep Learning for Augmentation of sRNA Expression Profiles

2019-09-26 · Jelena Fiosina, Maksims Fiosins, Stefan Bonn

The lack of well-structured metadata annotations complicates there-usability and interpretation of the growing amount of publicly available RNA expression data. The machine learning-based prediction of metadata(data augm…

Data Augmentation Deep Learning Feature Importance Prediction

Rumor Detection on Social Media with Reinforcement Learning-based Key Propagation Graph Generator

2024-05-21 · Yusong Zhang, Kun Xie, Xingyi Zhang, Xiangyu Dong 외

The spread of rumors on social media, particularly during significant events like the US elections and the COVID-19 pandemic, poses a serious threat to social stability and public health. Current rumor detection methods …

Data Augmentation Graph Neural Network

Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers

2026-07-11 · Christopher Buratti, Michele Marchetti, Federica Parlapiano, Davide Traini 외 arxiv

Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, such as the uneven importance of attention …