Cross-Modal Retrieval With Noisy Labels

2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)(2020)

引用 5|浏览13
暂无评分
摘要
Cross-modal retrieval is an important field of study for design of algorithms to effectively retrieve items from one modality when provided with a query from another modality. Recent progress in this field have shown that supervised algorithms perform significantly better than their unsupervised counterparts by utilizing the label information. In real scenarios, the labels are obtained through manual or automatic annotation, and thus are prone to errors. In this work, we systematically study the effect of label corruption on the performance of standard cross-modal algorithms. We propose a very simple, yet effective pre-processing framework which can help to mitigate the performance degradation suffered due to label corruption. First, the potentially more promising modality is automatically chosen, on which two different versions of a noise-resistant classification algorithm is trained to generate the pseudo-labels of the noisy cross-modal training data. The generated pseudo-labels can then be used by any cross-modal supervised approach to improve its performance. Extensive experiments across four cross-modal datasets with different types of label corruption show that the proposed framework gives impressive improvements for this important problem.
更多
查看译文
关键词
Cross-modal retrieval, cross-modal hashing, label corruption, symmetric noise, pairflip noise
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要