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

TL;DR

This paper introduces an adaptive, end-to-end graph convolutional network approach for multi-label image classification that learns graph topology and extends to multiple domains with adversarial training, achieving competitive results.

Contribution

It presents a novel adaptive graph learning architecture with attention and similarity strategies, extending multi-label classification to multiple domains.

Findings

Achieves competitive mean Average Precision (mAP) on benchmarks.

Reduces model size while maintaining performance.

Effectively extends to multi-domain scenarios with adversarial training.

Abstract

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.