Multi-Label Image Recognition With Graph Convolutional Networks
Top Cited Papers
- 1 June 2019
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5172-5181
- https://doi.org/10.1109/cvpr.2019.00532
Abstract
The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model the label dependencies to improve the recognition performance. To capture and explore such important dependencies, we propose a multi-label classification model based on Graph Convolutional Network (GCN). The model builds a directed graph over the object labels, where each node (label) is represented by word embeddings of a label, and GCN is learned to map this label graph into a set of inter-dependent object classifiers. These classifiers are applied to the image descriptors extracted by another sub-net, enabling the whole network to be end-to-end trainable. Furthermore, we propose a novel re-weighted scheme to create an effective label correlation matrix to guide information propagation among the nodes in GCN. Experiments on two multi-label image recognition datasets show that our approach obviously outperforms other existing state-of-the-art methods. In addition, visualization analyses reveal that the classifiers learned by our model maintain meaningful semantic topology.Keywords
This publication has 21 references indexed in Scilit:
- Human Attribute Recognition by Deep Hierarchical ContextsPublished by Springer Science and Business Media LLC ,2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- CNN-RNN: A Unified Framework for Multi-label Image ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Rethinking the Inception Architecture for Computer VisionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Exploit Bounding Box Annotations for Multi-Label Object RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Conditional Graphical Lasso for Multi-label Image ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- HCP: A Flexible CNN Framework for Multi-Label Image ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Recognizing Products: A Per-exemplar Multi-label Image Classification ApproachLecture Notes in Computer Science, 2014
- Glove: Global Vectors for Word RepresentationPublished by Association for Computational Linguistics (ACL) ,2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009