Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification

17 Dec 2019  ·  Renchun You, Zhiyao Guo, Lei Cui, Xiang Long, Yingze Bao, Shilei Wen ·

Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our novel cross-modality attention maps are generated with the guidance of learned label embeddings. Experiments on two multi-label image classification datasets (MS-COCO and NUS-WIDE) show our method outperforms other existing state-of-the-arts. In addition, we validate our method on a large multi-label video classification dataset (YouTube-8M Segments) and the evaluation results demonstrate the generalization capability of our method.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multi-Label Classification MS-COCO MS-CMA mAP 83.8 # 26
Multi-Label Classification NUS-WIDE MS-CMA MAP 61.4 # 8

Methods


No methods listed for this paper. Add relevant methods here