Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains
This work addresses the challenge of improving multi-label image classification accuracy and efficiency for researchers and practitioners in computer vision, though it is incremental as it builds on existing graph-based methods.
The paper tackled the problem of suboptimal pre-defined graph topologies and feature similarity loss in graph-based multi-label image classification by introducing an adaptive graph convolutional network with attention-based connectivity learning and similarity preservation, achieving competitive mean Average Precision (mAP) and model size compared to state-of-the-art methods on single and multi-domain benchmarks.
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.