Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning
This work addresses a specific inefficiency in semi-supervised learning for researchers and practitioners, offering an incremental improvement by optimizing sample utilization.
The paper tackles the problem of underutilized 'naive samples' in semi-supervised learning, where certain samples are already well-learned and do not contribute to model optimization, by proposing Sample Adaptive Augmentation (SAA) to augment these samples more diversely, resulting in accuracy improvements such as from 92.50% to 94.76% for FixMatch on CIFAR-10 with 40 labels.
In semi-supervised learning, unlabeled samples can be utilized through augmentation and consistency regularization. However, we observed certain samples, even undergoing strong augmentation, are still correctly classified with high confidence, resulting in a loss close to zero. It indicates that these samples have been already learned well and do not provide any additional optimization benefits to the model. We refer to these samples as ``naive samples". Unfortunately, existing SSL models overlook the characteristics of naive samples, and they just apply the same learning strategy to all samples. To further optimize the SSL model, we emphasize the importance of giving attention to naive samples and augmenting them in a more diverse manner. Sample adaptive augmentation (SAA) is proposed for this stated purpose and consists of two modules: 1) sample selection module; 2) sample augmentation module. Specifically, the sample selection module picks out {naive samples} based on historical training information at each epoch, then the naive samples will be augmented in a more diverse manner in the sample augmentation module. Thanks to the extreme ease of implementation of the above modules, SAA is advantageous for being simple and lightweight. We add SAA on top of FixMatch and FlexMatch respectively, and experiments demonstrate SAA can significantly improve the models. For example, SAA helped improve the accuracy of FixMatch from 92.50% to 94.76% and that of FlexMatch from 95.01% to 95.31% on CIFAR-10 with 40 labels.