Abstract | ||
---|---|---|
In this paper, we study the problem of learning image classification models in the presence of label noise. We revisit a simple compression regularization named Nested Dropout [22]. We find that Nested Dropout [22], though originally proposed to perform fast information retrieval and adaptive data compression, can properly regularize a neural network to combat label noise. Moreover, owing to its simplicity, it can be easily combined with Co-teaching [5] to further boost the performance. Our final model remains simple yet effective: it achieves comparable or even better performance than the state-of-the-art approaches on two real-world datasets with label noise which are Clothing1M [28] and ANIMAL-10N [24]. On Clothing1M [28], our approach obtains 74.9% accuracy which is slightly better than that of DivideMix [12]. On ANIMAL-10N [24], we achieve 84.1% accuracy while the best public result by PLC [30] is 83.4%. We hope that our simple approach can be served as a strong baseline for learning with label noise. Our implementation is available at https://github.com/yingyichen-cyy/Nested-Co-teaching. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPRW53098.2021.00302 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yingyi Chen | 1 | 0 | 0.68 |
Xi Shen | 2 | 0 | 0.68 |
Shell Xu Hu | 3 | 0 | 0.34 |
Johan A K Suykens | 4 | 2346 | 241.14 |