Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2203.04049 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929209013698560 |
|---|---|
| author | Yuan, Jin Chen, Shikai Zhang, Yao Shi, Zhongchao Geng, Xin Fan, Jianping Rui, Yong |
| author_facet | Yuan, Jin Chen, Shikai Zhang, Yao Shi, Zhongchao Geng, Xin Fan, Jianping Rui, Yong |
| contents | Multi-label classification aims to recognize multiple objects or attributes from images. However, it is challenging to learn from proper label graphs to effectively characterize such inter-label correlations or dependencies. Current methods often use the co-occurrence probability of labels based on the training set as the adjacency matrix to model this correlation, which is greatly limited by the dataset and affects the model's generalization ability. In this paper, we propose a Graph Attention Transformer Network (GATN), a general framework for multi-label image classification that can effectively mine complex inter-label relationships. First, we use the cosine similarity based on the label word embedding as the initial correlation matrix, which can represent rich semantic information. Subsequently, we design the graph attention transformer layer to transfer this adjacency matrix to adapt to the current domain. Our extensive experiments have demonstrated that our proposed methods can achieve state-of-the-art performance on three datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2203_04049 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Graph Attention Transformer Network for Multi-Label Image Classification Yuan, Jin Chen, Shikai Zhang, Yao Shi, Zhongchao Geng, Xin Fan, Jianping Rui, Yong Computer Vision and Pattern Recognition Multi-label classification aims to recognize multiple objects or attributes from images. However, it is challenging to learn from proper label graphs to effectively characterize such inter-label correlations or dependencies. Current methods often use the co-occurrence probability of labels based on the training set as the adjacency matrix to model this correlation, which is greatly limited by the dataset and affects the model's generalization ability. In this paper, we propose a Graph Attention Transformer Network (GATN), a general framework for multi-label image classification that can effectively mine complex inter-label relationships. First, we use the cosine similarity based on the label word embedding as the initial correlation matrix, which can represent rich semantic information. Subsequently, we design the graph attention transformer layer to transfer this adjacency matrix to adapt to the current domain. Our extensive experiments have demonstrated that our proposed methods can achieve state-of-the-art performance on three datasets. |
| title | Graph Attention Transformer Network for Multi-Label Image Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2203.04049 |