Qi Han, Kun Zhan, Zhibo Tian, Chengwei Xia
We lifted 16 functions out of this paper's own repositories and ran 10 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| kunzhan/infomatch | canonical | 6 of 8 |
| kunzhan/InfoMatch | — | 4 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| cal_time_p_and_p_model | Ran | kunzhan/InfoMatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("43872e13b837d9d6") |
| conv1x1 | Ran | kunzhan/infomatch/models/resnext.py pointer only (licence: NONE) · get_code("2a80220dabcb742a") |
| conv3x3 | Ran | kunzhan/infomatch/models/resnext.py pointer only (licence: NONE) · get_code("600ff2c45e0de056") |
| cutmix_hard | Ran | kunzhan/InfoMatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("866d8aa1a3657936") |
| de_interleave | Ran | kunzhan/InfoMatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("27ae5d495ffa4282") |
| default_loader | Ran | kunzhan/infomatch/dataset/ImageNet.py pointer only (licence: NONE) · get_code("9becbb1bb6878d86") |
| get_cosine_schedule_with_warmup | Ran | kunzhan/infomatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("99c1dcab51b21ada") |
| interleave | Ran | kunzhan/InfoMatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("f6043e7798bcabbd") |
| pil_loader | Ran | kunzhan/infomatch/dataset/ImageNet.py pointer only (licence: NONE) · get_code("f321f54723433661") |
| x_u_split | Ran | kunzhan/infomatch/dataset/ImageNet1.py pointer only (licence: NONE) · get_code("90e661c88d65afa0") |
| accimage_loader | Not yet run | kunzhan/infomatch/dataset/ImageNet.py pointer only (licence: NONE) · get_code("404fb2b2daa1ae78") |
| save_checkpoint | Not yet run | kunzhan/InfoMatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("853f415fdc5443ea") |
| setup_distributed | Not yet run | kunzhan/infomatch/dist_helper.py pointer only (licence: NONE) · get_code("ecf889acbcd26a3d") |
| test | Not yet run | kunzhan/InfoMatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("314a6334cf0478a8") |
| train | Not yet run | kunzhan/InfoMatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("6b7b164a79c03fc5") |
| warmup | Not yet run | kunzhan/InfoMatch/infoMatch_STL.py pointer only (licence: NONE) · get_code("7cd18ec60dcbf044") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2404.11003")
get_code_for_paper("2404.11003")
have("2404.11003")
Connect an agent — have() is free.