GM-MLIC: Graph Matching based Multi-Label Image Classification

Abstract

Multi-Label Image Classification (MLIC) aims to predict a set of labels that present in an image. The key to deal with such problem is to mine the associations between image contents and labels, and further obtain the correct assignments between images and their labels. In this paper, we treat each image as a bag of instances, and reformulate the task of MLIC as an instance-label matching selection problem. To model such problem, we propose a novel deep learning framework named Graph Matching based Multi-Label Image Classification (GM-MLIC), where Graph Matching (GM) scheme is introduced owing to its excellent capability of excavating the instance and label relationship. Specifically, we first construct an instance spatial graph and a label semantic graph respectively, and then incorporate them into a constructed assignment graph by connecting each instance to all labels. Subsequently, the graph network block is adopted to aggregate and update all nodes and edges state on the assignment graph to form structured representations for each instance and label. Our network finally derives a prediction score for each instance-label correspondence and optimizes such correspondence with a weighted cross-entropy loss. Extensive experiments conducted on various image datasets demonstrate the superiority of our proposed method.

arXiv commentAccepted by International Joint Conferences on Artificial Intelligence (IJCAI-2021)

References in corpus (9)

• CNN: Single-label to Multi-label
• Deep Convolutional Ranking for Multilabel Image Annotation
• CNN-RNN: A Unified Framework for Multi-label Image Classification
• Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
• Multi-Label Image Recognition with Graph Convolutional Networks
• Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
• Multi-label Image Recognition by Recurrently Discovering Attentional Regions
• Chest X-rays Classification: A Multi-Label and Fine-Grained Problem
• Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification