Bo Han, Jianing Zhu, Tongliang Liu, Jiangchao Yao, Jianliang Xu, Hengzhuang Li
We lifted 7 functions out of this paper's own repositories and ran 2 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 |
|---|---|---|
| tmlr-group/unleashing-mask | canonical | 2 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| fpr_and_fdr_at_recall | Ran | tmlr-group/unleashing-mask/utils/get_scores.py code served (permissive licence) · get_code("3853ecdb6fc74451") |
| stable_cumsum | Ran | tmlr-group/unleashing-mask/utils/get_scores.py code served (permissive licence) · get_code("d4acb3120a027622") |
| accumulate | Not yet run | tmlr-group/unleashing-mask/utils/net_utils.py code served (permissive licence) · get_code("8a42a6951b0c5e57") |
| arg_to_varname | Not yet run | tmlr-group/unleashing-mask/configs/parser.py code served (permissive licence) · get_code("177a4abf40724f6e") |
| argv_to_vars | Not yet run | tmlr-group/unleashing-mask/configs/parser.py code served (permissive licence) · get_code("ffc9d7cced6f71fb") |
| get_lr | Not yet run | tmlr-group/unleashing-mask/utils/net_utils.py code served (permissive licence) · get_code("717f5458343a0b63") |
| trim_preceding_hyphens | Not yet run | tmlr-group/unleashing-mask/configs/parser.py code served (permissive licence) · get_code("a99f170ebd682af5") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machine learning models in real-world applications. Previous paradigms either explore better scoring functions or utilize the knowledge of outliers to equip the models with the ability of OOD detection. However, few of them pay attention to the intrinsic OOD detection capability of the given model. In this work, we generally discover the existence of an intermediate stage of a model trained on in-distribution (ID) data having higher OOD detection performance than that of its final stage across different settings, and further identify one critical data-level attribution to be learning with the atypical samples. Based on such insights, we propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data. Our method utilizes a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them. Extensive experiments and analysis demonstrate the effectiveness of our method. The code is available at: https://github.com/ tmlr-group/Unleashing-Mask.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2306.03715")
get_code_for_paper("2306.03715")
have("2306.03715")
Connect an agent — have() is free.