Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Singh, Indel Pal, Ghorbel, Enjie, Oyedotun, Oyebade, Aouada, Djamila
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916330561601536
author Singh, Indel Pal
Ghorbel, Enjie
Oyedotun, Oyebade
Aouada, Djamila
author_facet Singh, Indel Pal
Ghorbel, Enjie
Oyedotun, Oyebade
Aouada, Djamila
contents This paper proposes an adaptive graph-based approach for multi-label image classification. Graph-based methods have been largely exploited in the field of multi-label classification, given their ability to model label correlations. Specifically, their effectiveness has been proven not only when considering a single domain but also when taking into account multiple domains. However, the topology of the used graph is not optimal as it is pre-defined heuristically. In addition, consecutive Graph Convolutional Network (GCN) aggregations tend to destroy the feature similarity. To overcome these issues, an architecture for learning the graph connectivity in an end-to-end fashion is introduced. This is done by integrating an attention-based mechanism and a similarity-preserving strategy. The proposed framework is then extended to multiple domains using an adversarial training scheme. Numerous experiments are reported on well-known single-domain and multi-domain benchmarks. The results demonstrate that our approach achieves competitive results in terms of mean Average Precision (mAP) and model size as compared to the state-of-the-art. The code will be made publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2301_04494
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains
Singh, Indel Pal
Ghorbel, Enjie
Oyedotun, Oyebade
Aouada, Djamila
Computer Vision and Pattern Recognition
This paper proposes an adaptive graph-based approach for multi-label image classification. Graph-based methods have been largely exploited in the field of multi-label classification, given their ability to model label correlations. Specifically, their effectiveness has been proven not only when considering a single domain but also when taking into account multiple domains. However, the topology of the used graph is not optimal as it is pre-defined heuristically. In addition, consecutive Graph Convolutional Network (GCN) aggregations tend to destroy the feature similarity. To overcome these issues, an architecture for learning the graph connectivity in an end-to-end fashion is introduced. This is done by integrating an attention-based mechanism and a similarity-preserving strategy. The proposed framework is then extended to multiple domains using an adversarial training scheme. Numerous experiments are reported on well-known single-domain and multi-domain benchmarks. The results demonstrate that our approach achieves competitive results in terms of mean Average Precision (mAP) and model size as compared to the state-of-the-art. The code will be made publicly available.
title Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2301.04494