TY - GEN
T1 - Learning from noisy labels via discrepant collaborative training
AU - Han, Yan
AU - Roy, Soumava Kumar
AU - Petersson, Lars
AU - Harandi, Mehrtash
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/3
Y1 - 2020/3
N2 - Noise is ubiquitous in the world around us. Difficulty in estimating the noise within a dataset makes learning from such a dataset a difficult and challenging task. In this paper, we propose a novel and effective learning framework in order to alleviate the adverse effects of noise within a dataset. Towards this aim, we modify a collaborative training framework to utilize discrepancy constraints between respective feature extractors enabling the learning of distinct, yet discriminative features, pacifying the adverse effects of noise. Empirical results of our proposed algorithm, Discrepant Collaborative Training (DCT), achieve competitive results against several current state-of-the-art algorithms across MNIST, CIFAR10 and CIFAR100, as well as large fine-grained image classification datasets such as CUBS-200-2011 and CARS196 for different levels of noise.
AB - Noise is ubiquitous in the world around us. Difficulty in estimating the noise within a dataset makes learning from such a dataset a difficult and challenging task. In this paper, we propose a novel and effective learning framework in order to alleviate the adverse effects of noise within a dataset. Towards this aim, we modify a collaborative training framework to utilize discrepancy constraints between respective feature extractors enabling the learning of distinct, yet discriminative features, pacifying the adverse effects of noise. Empirical results of our proposed algorithm, Discrepant Collaborative Training (DCT), achieve competitive results against several current state-of-the-art algorithms across MNIST, CIFAR10 and CIFAR100, as well as large fine-grained image classification datasets such as CUBS-200-2011 and CARS196 for different levels of noise.
UR - http://www.scopus.com/inward/record.url?scp=85085492418&partnerID=8YFLogxK
U2 - 10.1109/WACV45572.2020.9093619
DO - 10.1109/WACV45572.2020.9093619
M3 - Conference contribution
T3 - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
SP - 3158
EP - 3167
BT - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
Y2 - 1 March 2020 through 5 March 2020
ER -