Class-Level Confidence Based 3D Semi-Supervised Learning

Current pseudo-labeling strategies in 3D semi-supervised learning (SSL) fail to dynamically incorporate the variance of learning status which is affected by each class’s learning difficulty and data imbalance. To address this problem, we practically demonstrate that 3D unlabeled data class-level confidence can represent the learning status. Based on this finding, we present a novel class-level confidence based 3D SSL method. Firstly, a dynamic thresholding strategy is proposed to utilize more unlabeled data, especially for low learning status classes. Then, a re-sampling strategy is designed to avoid biasing toward high learning status classes, which dynamically changes the sampling probability of each class. Unlike the latest state-of-the-art SSL method FlexMatch which also utilizes dynamic threshold, our method can be applied to the inherently imbalanced dataset and thus is more general. To show the effectiveness of our method in 3D SSL tasks, we conduct extensive experiments on 3D SSL classification and detection tasks. Our method significantly outperforms state-of-the-art counterparts for both 3D SSL classification and detection tasks in all datasets.

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)