Co-sampling: Training Robust Networks for Extremely Noisy Supervision
share
Training robust deep networks is challenging under noisy labels. Current methodologies focus on estimating the noise transition matrix. However, this matrix is not easy to be estimated exactly. In this paper, free of the matrix estimation, we present a simple but robust learning paradigm called "Co-sampling", which can train deep networks robustly under extremely noisy labels. Briefly, our paradigm trains two networks simultaneously. In each mini-batch data, each network samples its small-loss instances, and cross-trains on such instances from its peer network. We conduct experiments on several simulated noisy datasets. Empirical results demonstrate that, under extremely noisy labels, the Co-sampling approach trains deep learning models robustly.
READ FULL TEXT
