Learning from Noisy Labels via Discrepant Collaborative Training

Yan Han, SOUMAVA KUMAR ROY, Lars Petersson, Mehrtash Harandi

Abstract: 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 pa-per, 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 train-ing framework to utilize discrepancy constraints between respective feature extractors enabling the learning of dis-tinct, 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 asCUBS-200-2011 and CARS196 for different levels of noise.