dc.contributor.author | Dubey, Abhimanyu | |
dc.contributor.author | Gupta, Otkrist | |
dc.contributor.author | Guo, Pei | |
dc.contributor.author | Raskar, Ramesh | |
dc.contributor.author | Farrell, Ryan | |
dc.date.accessioned | 2021-11-10T15:56:28Z | |
dc.date.available | 2021-11-10T12:34:50Z | |
dc.date.available | 2021-11-10T15:56:28Z | |
dc.date.issued | 2018-07 | |
dc.identifier.uri | https://hdl.handle.net/1721.1/138096.2 | |
dc.description.abstract | © Springer Nature Switzerland AG 2018. Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity. While prior work has addressed intra-class variation using localization and segmentation techniques, inter-class similarity may also affect feature learning and reduce classification performance. In this work, we address this problem using a novel optimization procedure for the end-to-end neural network training on FGVC tasks. Our procedure, called Pairwise Confusion (PC) reduces overfitting by intentionally introducing confusion in the activations. With PC regularization, we obtain state-of-the-art performance on six of the most widely-used FGVC datasets and demonstrate improved localization ability. PC is easy to implement, does not need excessive hyperparameter tuning during training, and does not add significant overhead during test time. | en_US |
dc.language.iso | en | |
dc.publisher | Springer International Publishing | en_US |
dc.relation.isversionof | 10.1007/978-3-030-01258-8_5 | en_US |
dc.rights | Creative Commons Attribution-Noncommercial-Share Alike | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ | en_US |
dc.source | arXiv | en_US |
dc.title | Pairwise confusion for fine-grained visual classification | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Dubey, Abhimanyu, Gupta, Otkrist, Guo, Pei, Raskar, Ramesh and Farrell, Ryan. 2018. "Pairwise confusion for fine-grained visual classification." | en_US |
dc.contributor.department | Program in Media Arts and Sciences (Massachusetts Institute of Technology) | en_US |
dc.eprint.version | Original manuscript | en_US |
dc.type.uri | http://purl.org/eprint/type/ConferencePaper | en_US |
eprint.status | http://purl.org/eprint/status/NonPeerReviewed | en_US |
dc.date.updated | 2019-08-02T14:26:17Z | |
dspace.date.submission | 2019-08-02T14:26:18Z | |
mit.metadata.status | Publication Information Needed | en_US |