feat: add-kpca#315
Open
fanghenshaometeor wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds Kernel PCA (KPCA) as a new post-hoc OOD postprocessor.
The core idea of this KPCA detection method is two-fold: (i) identifying a suitable kernel to capture the hidden non-linearity in ID and OOD data, thereby inducing a separable feature subspace; and (ii) approximating this kernel in a task-driven and highly-efficient manner for scalability on large-scale data.
The KPCA detection method has been published in NeurIPS'24 and TPAMI'26. The conference version identifies the kernel and uses a data-independent approximation method. The journal version justifies the selected kernel with more explanations, supports an enhanced data-dependent approximation technique, and further discusses kernel learning for OOD detection.
Paper: neurips24 and tpami26
Reference code: neurips24 and tpami26