Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Open-Set Noise and Utilizing Hard Examples

Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:
Journal Article
Citation:
IEEE Transactions on Multimedia, 2021, PP, (99), pp. 1-1
Issue Date:
2021-01-01
Filename Description Size
2-s2.0-85100762592 am.pdfAccepted Manuscript Version5.51 MB
Adobe PDF
Full metadata record
Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention. However, the presence of label noise and hard examples in web images are two obstacles for training robust fine-grained recognition models. To this end, in this paper, we propose a novel approach to remove irrelevant samples from real-world web images during training, while employing useful hard examples to update the network. Thus, our approach can alleviate the harmful effects of irrelevant noisy web images and hard examples to achieve better performance. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is far superior to current state-of-the-art web-supervised methods.
Please use this identifier to cite or link to this item: