SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.04606 · 2018

Deep Anomaly Detection with Outlier Exposure

Dan Hendrycks, Mantas Mazeika, Thomas Dietterich

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 5 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
GaussianLayer Ran guyAmit/GLOD/FOOD/Gaussain_layer.py
pointer only (licence: NONE) · get_code("04a6bca8fa7ea2c2")
OELoss Ran AlexMeinke/Provable-OOD-Detection/utils/traintest/losses.py
code served (permissive licence) · get_code("7e2caa67572f6723")
OE_300k_dataloader Ran jun-cen/unified_open_set_recognition/UOSR_train/bit_pytorch/oe_bit.py
pointer only (licence: NONE) · get_code("a720f50e53abe705")
get_loss_baseline Ran oliverzhang42/ood_medical_images/src/losses.py
pointer only (licence: NONE) · get_code("40f6f2dd97282786")
get_loss_outlier_exposure Ran oliverzhang42/ood_medical_images/src/losses.py
pointer only (licence: NONE) · get_code("9a2f19557ae1a813")

Repositories linked to this paper

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

Abstract

It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We propose leveraging these data to improve deep anomaly detection by training anomaly detectors against an auxiliary dataset of outliers, an approach we call Outlier Exposure (OE). This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments on natural language processing and small-and large-scale vision tasks, we find that Outlier Exposure significantly improves detection performance. We also observe that cutting-edge generative models trained on CIFAR-10 may assign higher likelihoods to SVHN images than to CIFAR-10 images; we use OE to mitigate this issue. We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.

For agents

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

get_harvested_code_for_paper("1812.04606")
get_code_for_paper("1812.04606")
have("1812.04606")

Connect an agent — have() is free.