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

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.

References in corpus (10)

• Conditional Generative Adversarial Nets
• AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
• Conditional Adversarial Domain Adaptation
• CNN: Single-label to Multi-label
• Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classification
• Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition
• Relation Network for Multi-label Aerial Image Classification
• DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations
• Multi-layered Semantic Representation Network for Multi-label Image Classification
• Learning Category Correlations for Multi-label Image Recognition with Graph Networks