Doubly Robust Self-Training
This addresses a key bottleneck in semi-supervised learning for practitioners in computer vision and autonomous driving, though it appears incremental as it builds directly on standard self-training.
The paper tackles the problem of self-training's sensitivity to pseudo-label accuracy in semi-supervised learning by introducing a doubly robust algorithm that adapts between using only labeled data when pseudo-labels are incorrect and using all data when they are accurate, demonstrating superiority over baselines on ImageNet and nuScenes datasets.
Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of self-training heavily relies on the accuracy of these pseudo-labels. In this paper, we introduce doubly robust self-training, a novel semi-supervised algorithm that provably balances between two extremes. When the pseudo-labels are entirely incorrect, our method reduces to a training process solely using labeled data. Conversely, when the pseudo-labels are completely accurate, our method transforms into a training process utilizing all pseudo-labeled data and labeled data, thus increasing the effective sample size. Through empirical evaluations on both the ImageNet dataset for image classification and the nuScenes autonomous driving dataset for 3D object detection, we demonstrate the superiority of the doubly robust loss over the standard self-training baseline.