SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.01879 · CVPR · 2021

MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space

Yixuan Li, Rui Huang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 3 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.

FunctionStatusWhere it lives
calc_group_softmax_loss Ran deeplearning-wisc/large_scale_ood/finetune.py
code served (permissive licence) · get_code("1caff2f8b8fc899d")
get_Mahalanobis_score Ran deeplearning-wisc/gradnorm_ood/utils/mahalanobis_lib.py
code served (permissive licence) · get_code("ae64ecb508b5b2bb")
iterate_data_mahalanobis Ran tmlr-group/class_prior/funcs.py
code served (permissive licence) · get_code("12fc2270fe050752")
CLIP Not yet run ma-kjh/CMA-OoDD/clip/model.py
pointer only (licence: NONE) · get_code("ef2d645ece6b584c")

Repositories linked to this paper

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

Abstract

Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world. Existing solutions are mainly driven by small datasets, with low resolution and very few class labels (e.g., CIFAR). As a result, OOD detection for largescale image classification tasks remains largely unexplored. In this paper, we bridge this critical gap by proposing a group-based OOD detection framework, along with a novel OOD scoring function termed MOS. Our key idea is to decompose the large semantic space into smaller groups with similar concepts, which allows simplifying the decision boundaries between in-vs. out-of-distribution data for effective OOD detection. Our method scales substantially better for high-dimensional class space than previous approaches. We evaluate models trained on ImageNet against four carefully curated OOD datasets, spanning diverse semantics. MOS establishes state-of-the-art performance, reducing the average FPR95 by 14.33% while achieving 6x speedup in inference compared to the previous best method.

For agents

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

get_harvested_code_for_paper("2105.01879")
get_code_for_paper("2105.01879")
have("2105.01879")

Connect an agent — have() is free.