A Novel Self-Supervised Re-labeling Approach for Training with Noisy Labels
This addresses the challenge of noisy labels in deep learning, which is critical for real-world applications where clean data is scarce, but it is an incremental improvement over existing methods like Co-teaching.
The paper tackles the problem of training deep learning models with noisy labels by proposing mCT-S2R, a method combining self-supervision, co-teaching, and re-labeling, which achieves improved performance on three standard datasets.
The major driving force behind the immense success of deep learning models is the availability of large datasets along with their clean labels. Unfortunately, this is very difficult to obtain, which has motivated research on the training of deep models in the presence of label noise and ways to avoid over-fitting on the noisy labels. In this work, we build upon the seminal work in this area, Co-teaching and propose a simple, yet efficient approach termed mCT-S2R (modified co-teaching with self-supervision and re-labeling) for this task. First, to deal with significant amount of noise in the labels, we propose to use self-supervision to generate robust features without using any labels. Next, using a parallel network architecture, an estimate of the clean labeled portion of the data is obtained. Finally, using this data, a portion of the estimated noisy labeled portion is re-labeled, before resuming the network training with the augmented data. Extensive experiments on three standard datasets show the effectiveness of the proposed framework.