Pairwise confusion for fine-grained visual classification
Name
1705.08016.pdf
Description
Submitted version
Size
964.49 KB
Format
Unknown
Checksum (MD5)
c27d0440e14238837e36ba7a6f3cc662
Author(s)
Dubey, Abhimanyu
Gupta, Otkrist
Guo, Pei
Raskar, Ramesh
Farrell, Ryan
Date Issued
July 2018
Publisher
Springer International Publishing
Citation
Dubey, Abhimanyu, Gupta, Otkrist, Guo, Pei, Raskar, Ramesh and Farrell, Ryan. 2018. "Pairwise confusion for fine-grained visual classification."
Version
Original manuscript
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.
MIT Department
Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-01258-8_5
