SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02949 · NeurIPS · 2024

Kernel PCA for Out-of-Distribution Detection

Xiaolin Huang, Jie Yang, Qinghua Tao, Kun Fang, Kexin Lv, Mingzhen He

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 4 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.

RepositoryRoleRan
fanghenshaometeor/ood-kpca-extension — 2 of 3
copy not recorded — 2 of 2
FunctionStatusWhere it lives
fpr_and_fdr_at_recall Ran this paper's copy was not recorded; identical code first harvested from fanghenshaometeor/ood-kernel-pca-ext
pointer only · get_code("e1dfe697d81dc165")
iterate_data_react Ran fanghenshaometeor/ood-kpca-extension/utils_ood.py
pointer only (licence: NONE) · get_code("5dcd5cdb8a08e275")
stable_cumsum Ran this paper's copy was not recorded; identical code first harvested from fanghenshaometeor/ood-kernel-pca-ext
pointer only · get_code("d4acb3120a027622")
val_ood_fuse Ran fanghenshaometeor/ood-kpca-extension/utils_ood.py
pointer only (licence: NONE) · get_code("48e491ddc2c394f5")
get_measures Not yet run fanghenshaometeor/ood-kpca-extension/utils_ood.py
pointer only (licence: NONE) · get_code("914e5f1ab3d0dfdf")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Out-of-Distribution (OoD) detection is vital for the reliability of Deep Neural Networks (DNNs). Existing works have shown the insufficiency of Principal Component Analysis (PCA) straightforwardly applied on the features of DNNs in detecting OoD data from In-Distribution (InD) data. The failure of PCA suggests that the network features residing in OoD and InD are not well separated by simply proceeding in a linear subspace, which instead can be resolved through proper non-linear mappings. In this work, we leverage the framework of Kernel PCA (KPCA) for OoD detection, and seek suitable non-linear kernels that advocate the separability between InD and OoD data in the subspace spanned by the principal components. Besides, explicit feature mappings induced from the devoted taskspecific kernels are adopted so that the KPCA reconstruction error for new test samples can be efficiently obtained with large-scale data. Extensive theoretical and empirical results on multiple OoD data sets and network structures verify the superiority of our KPCA detector in efficiency and efficacy with state-of-the-art detection performance.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.02949")
get_code_for_paper("2402.02949")
have("2402.02949")

Connect an agent — have() is free.