SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.03061 · 2022

Back to the Basics: Revisiting Out-of-Distribution Detection Baselines

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 6 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
cleanlab/ood-detection-benchmarks canonical 6 of 6
FunctionStatusWhere it lives
find_dupes_in_data_dir Ran cleanlab/ood-detection-benchmarks/src/preprocess/remove_dupes.py
code served (permissive licence) · get_code("137e31a502097297")
find_dupes_in_data_split_dir Ran cleanlab/ood-detection-benchmarks/src/preprocess/remove_dupes.py
code served (permissive licence) · get_code("a8307d3e9159b810")
fit_mahalanobis Ran cleanlab/ood-detection-benchmarks/src/experiments/OOD/mahalanobis.py
code served (permissive licence) · get_code("4d49690d4932ba8c")
fit_rmd Ran cleanlab/ood-detection-benchmarks/src/experiments/OOD/mahalanobis.py
code served (permissive licence) · get_code("cc65480057d34f19")
score_mahalanobis Ran cleanlab/ood-detection-benchmarks/src/experiments/OOD/mahalanobis.py
code served (permissive licence) · get_code("1e5ce5936af7b546")
timefunc Ran cleanlab/ood-detection-benchmarks/src/utils/time_utils.py
code served (permissive licence) · get_code("f88aae44b2b0fdac")

Repositories linked to this paper

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

Abstract

We study simple methods for out-of-distribution (OOD) image detection that are compatible with any already trained classifier, relying on only its predictions or learned representations. Evaluating the OOD detection performance of various methods when utilized with ResNet-50 and Swin Transformer models, we find methods that solely consider the model's predictions can be easily outperformed by also considering the learned representations. Based on our analysis, we advocate for a dead-simple approach that has been neglected in other studies: simply flag as OOD images whose average distance to their K nearest neighbors is large (in the representation space of an image classifier trained on the in-distribution data).

For agents

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

get_harvested_code_for_paper("2207.03061")
get_code_for_paper("2207.03061")
have("2207.03061")

Connect an agent — have() is free.