Visual Neural Decoding via Improved Visual-EEG Semantic Consistency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Hongzhou, He, Lianghua, Liu, Yihang, Yang, Longzhen, Shang, Shaohua, Zhou, MengChu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918421925462016
author Chen, Hongzhou
He, Lianghua
Liu, Yihang
Yang, Longzhen
Shang, Shaohua
Zhou, MengChu
author_facet Chen, Hongzhou
He, Lianghua
Liu, Yihang
Yang, Longzhen
Shang, Shaohua
Zhou, MengChu
contents Visual neural decoding aims to extract and interpret original visual experiences directly from human brain activity. Recent studies have demonstrated the feasibility of decoding visual semantic categories from electroencephalography (EEG) signals, among which metric learning-based approaches have delivered promising results. However, these methods that directly map EEG features into a pre-trained embedding space inevitably introduce mapping bias, resulting in a modality gap and semantic inconsistency that impair cross-modal alignment. To address these issues, this work constructs a Visual-EEG Joint Semantic Space to bridge the gap between visual images and neural signals. Building upon this space, we propose two novel approaches to improve semantic consistency between cross-modal representations and facilitate optimal alignment. Specifically, (1) we introduce a Visual-EEG Semantic Decoupling Network (VE-SDN) to explicitly disentangle semantic components from modality representations, thereby achieving purely semantic-level cross-modal alignment. (2) We introduce a Neural-Guided Intra-Class Consistency (NGIC) objective, an asymmetric representation alignment strategy designed to effectively enhance the robustness of visual representations and further boost decoding performance. Extensive experiments on a large-scale Visual-EEG dataset validate the effectiveness of the proposed method. Compared to the strongest baseline, our approach demonstrates superior decoding performance, yielding relative Top-1/Top-5 accuracy improvements of 38.9%/17.9% in intra-subject and 16.1%/11.3% in inter-subject settings. The code is available at https://github.com/hzalanchen/Cross-Modal-EEG
format Preprint
id arxiv_https___arxiv_org_abs_2408_06788
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Visual Neural Decoding via Improved Visual-EEG Semantic Consistency
Chen, Hongzhou
He, Lianghua
Liu, Yihang
Yang, Longzhen
Shang, Shaohua
Zhou, MengChu
Computer Vision and Pattern Recognition
Human-Computer Interaction
Visual neural decoding aims to extract and interpret original visual experiences directly from human brain activity. Recent studies have demonstrated the feasibility of decoding visual semantic categories from electroencephalography (EEG) signals, among which metric learning-based approaches have delivered promising results. However, these methods that directly map EEG features into a pre-trained embedding space inevitably introduce mapping bias, resulting in a modality gap and semantic inconsistency that impair cross-modal alignment. To address these issues, this work constructs a Visual-EEG Joint Semantic Space to bridge the gap between visual images and neural signals. Building upon this space, we propose two novel approaches to improve semantic consistency between cross-modal representations and facilitate optimal alignment. Specifically, (1) we introduce a Visual-EEG Semantic Decoupling Network (VE-SDN) to explicitly disentangle semantic components from modality representations, thereby achieving purely semantic-level cross-modal alignment. (2) We introduce a Neural-Guided Intra-Class Consistency (NGIC) objective, an asymmetric representation alignment strategy designed to effectively enhance the robustness of visual representations and further boost decoding performance. Extensive experiments on a large-scale Visual-EEG dataset validate the effectiveness of the proposed method. Compared to the strongest baseline, our approach demonstrates superior decoding performance, yielding relative Top-1/Top-5 accuracy improvements of 38.9%/17.9% in intra-subject and 16.1%/11.3% in inter-subject settings. The code is available at https://github.com/hzalanchen/Cross-Modal-EEG
title Visual Neural Decoding via Improved Visual-EEG Semantic Consistency
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2408.06788