InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913347688988672 |
|---|---|
| author | Han, Qi Tian, Zhibo Xia, Chengwei Zhan, Kun |
| author_facet | Han, Qi Tian, Zhibo Xia, Chengwei Zhan, Kun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11003 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification Han, Qi Tian, Zhibo Xia, Chengwei Zhan, Kun Computer Vision and Pattern Recognition 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. |
| title | InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.11003 |