Extracting Useful Knowledge from Noisy Web Images via Data Purification for Fine-Grained Recognition
Lists
Only you see this
Abstract
Fine-grained visual recognition tasks typically require training data with reliable acquisition and annotation processes. Acquiring such datasets with precise fine-grained annotations is very expensive and time-consuming. Conversely, a vast amount of web data is relatively easy to obtain with nearly no human effort. Nevertheless, the presence of label noise in web images becomes a huge obstacle for training robust fine-grained recognition models. In this work, we investigate the noisy label problem and propose a method that can specifically distinguish in- and out-of-distribution noisy samples. It can purify the web training data by discarding out-of-distribution noisy images and relabeling in-distribution ones. After purification, we can train the model on a less noisy web training set to achieve better robustness and performance. Extensive experiments on three real-world web datasets for fine-grained visual recognition demonstrate the superiority of our approach.
BibTeX
@inproceedings{zhang2021extracting,
author = {Chuanyi Zhang and Yazhou Yao and Xing Xu and Jie Shao and Jingkuan Song and Zechao Li and Zhenmin Tang},
title = {{Extracting Useful Knowledge from Noisy Web Images via Data Purification for Fine-Grained Recognition}},
booktitle = {ACM Multimedia},
year = {2021},
doi = {10.1145/3474085.3475536},
}Loading related content...