Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones
Year: 2021
Type: preprint
Abstract: 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. Therefore, in this paper, we propose a novel approach for removing 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.
Source: arXiv (Cornell University)
Institution: Nanjing University of Science and Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3164854065