InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification
This work addresses a key bottleneck in semi-supervised learning for image classification, though it appears incremental as it builds on existing methods like contrastive learning.
The paper tackles the challenge of fully exploiting unlabeled data in semi-supervised image classification by using information entropy neural estimation, achieving superior performance in experiments.
Semi-supervised image classification, leveraging pseudo supervision and consistency regularization, has demonstrated remarkable success. However, the ongoing challenge lies in fully exploiting the potential of unlabeled data. To address this, we employ information entropy neural estimation to utilize the potential of unlabeled samples. Inspired by contrastive learning, the entropy is estimated by maximizing a lower bound on mutual information across different augmented views. Moreover, we theoretically analyze that the information entropy of the posterior of an image classifier is approximated by maximizing the likelihood function of the softmax predictions. Guided by these insights, we optimize our model from both perspectives to ensure that the predicted probability distribution closely aligns with the ground-truth distribution. Given the theoretical connection to information entropy, we name our method InfoMatch. Through extensive experiments, we show its superior performance. The source code is available at https://github.com/kunzhan/InfoMatch.