Saved in:
Bibliographic Details
Main Authors: Tian, Yukun, Chen, Hao, Deng, Yongjian, Shen, Feihong, Liu, Kepan, You, Wei, Zhang, Ziyang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.11813
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916399549513728
author Tian, Yukun
Chen, Hao
Deng, Yongjian
Shen, Feihong
Liu, Kepan
You, Wei
Zhang, Ziyang
author_facet Tian, Yukun
Chen, Hao
Deng, Yongjian
Shen, Feihong
Liu, Kepan
You, Wei
Zhang, Ziyang
contents The event camera has demonstrated significant success across a wide range of areas due to its low time latency and high dynamic range. However, the community faces challenges such as data deficiency and limited diversity, often resulting in over-fitting and inadequate feature learning. Notably, the exploration of data augmentation techniques in the event community remains scarce. This work aims to address this gap by introducing a systematic augmentation scheme named EventAug to enrich spatial-temporal diversity. In particular, we first propose Multi-scale Temporal Integration (MSTI) to diversify the motion speed of objects, then introduce Spatial-salient Event Mask (SSEM) and Temporal-salient Event Mask (TSEM) to enrich object variants. Our EventAug can facilitate models learning with richer motion patterns, object variants and local spatio-temporal relations, thus improving model robustness to varied moving speeds, occlusions, and action disruptions. Experiment results show that our augmentation method consistently yields significant improvements across different tasks and backbones (e.g., a 4.87% accuracy gain on DVS128 Gesture). Our code will be publicly available for this community.
format Preprint
id arxiv_https___arxiv_org_abs_2409_11813
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EventAug: Multifaceted Spatio-Temporal Data Augmentation Methods for Event-based Learning
Tian, Yukun
Chen, Hao
Deng, Yongjian
Shen, Feihong
Liu, Kepan
You, Wei
Zhang, Ziyang
Computer Vision and Pattern Recognition
Artificial Intelligence
The event camera has demonstrated significant success across a wide range of areas due to its low time latency and high dynamic range. However, the community faces challenges such as data deficiency and limited diversity, often resulting in over-fitting and inadequate feature learning. Notably, the exploration of data augmentation techniques in the event community remains scarce. This work aims to address this gap by introducing a systematic augmentation scheme named EventAug to enrich spatial-temporal diversity. In particular, we first propose Multi-scale Temporal Integration (MSTI) to diversify the motion speed of objects, then introduce Spatial-salient Event Mask (SSEM) and Temporal-salient Event Mask (TSEM) to enrich object variants. Our EventAug can facilitate models learning with richer motion patterns, object variants and local spatio-temporal relations, thus improving model robustness to varied moving speeds, occlusions, and action disruptions. Experiment results show that our augmentation method consistently yields significant improvements across different tasks and backbones (e.g., a 4.87% accuracy gain on DVS128 Gesture). Our code will be publicly available for this community.
title EventAug: Multifaceted Spatio-Temporal Data Augmentation Methods for Event-based Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2409.11813