SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.00337 · 2021

A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 14 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
daintlab/unknown-detection-benchmarks canonical 14 of 15
FunctionStatusWhere it lives
accuracy Ran daintlab/unknown-detection-benchmarks/utils.py
code served (permissive licence) · get_code("67a13c0cb19afb83")
aurc_eaurc Ran daintlab/unknown-detection-benchmarks/metrics_md.py
code served (permissive licence) · get_code("612bae70040c203f")
conv1x1 Ran daintlab/unknown-detection-benchmarks/models/resnet_imagenet.py
code served (permissive licence) · get_code("d9def42110729a85")
conv3x3 Ran daintlab/unknown-detection-benchmarks/models/resnet_imagenet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
conv3x3 Ran daintlab/unknown-detection-benchmarks/models/resnet_cifar.py
code served (permissive licence) · get_code("6af95ebe99af2e36")
float_parameter Ran daintlab/unknown-detection-benchmarks/methods/augmix/augmentations.py
code served (permissive licence) · get_code("be1cf2403304fa6d")
get_curve Ran daintlab/unknown-detection-benchmarks/metrics_ood.py
code served (permissive licence) · get_code("ed35359a5c2b419c")
in_dist_loader Ran daintlab/unknown-detection-benchmarks/dataloader.py
code served (permissive licence) · get_code("1693518f0ab9445d")
int_parameter Ran daintlab/unknown-detection-benchmarks/methods/augmix/augmentations.py
code served (permissive licence) · get_code("beaa91443124b324")
one_hot_embedding Ran daintlab/unknown-detection-benchmarks/utils.py
code served (permissive licence) · get_code("d018404cd06ecc3f")
sample_level Ran daintlab/unknown-detection-benchmarks/methods/augmix/augmentations.py
code served (permissive licence) · get_code("5cc8d4764ac07a35")
str2bool Ran daintlab/unknown-detection-benchmarks/utils.py
code served (permissive licence) · get_code("9052013b7e166b05")
trn_loader Ran daintlab/unknown-detection-benchmarks/dataloader.py
code served (permissive licence) · get_code("10d0fca58f787cd4")
tst_loader Ran daintlab/unknown-detection-benchmarks/dataloader.py
code served (permissive licence) · get_code("d3690f3ae6c59a20")
resnet18 Not yet run daintlab/unknown-detection-benchmarks/models/resnet_imagenet.py
code served (permissive licence) · get_code("f1558cd7a9612567")

Repositories linked to this paper

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

Abstract

Deep neural networks have achieved outstanding performance over various tasks, but they have a critical issue: over-confident predictions even for completely unknown samples. Many studies have been proposed to successfully filter out these unknown samples, but they only considered narrow and specific tasks, referred to as misclassification detection, open-set recognition, or out-of-distribution detection. In this work, we argue that these tasks should be treated as fundamentally an identical problem because an ideal model should possess detection capability for all those tasks. Therefore, we introduce the unknown detection task, an integration of previous individual tasks, for a rigorous examination of the detection capability of deep neural networks on a wide spectrum of unknown samples. To this end, unified benchmark datasets on different scales were constructed and the unknown detection capabilities of existing popular methods were subject to comparison. We found that Deep Ensemble consistently outperforms the other approaches in detecting unknowns; however, all methods are only successful for a specific type of unknown. The reproducible code and benchmark datasets are available at https://github.com/daintlab/unknown-detection-benchmarks .

For agents

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

get_harvested_code_for_paper("2112.00337")
get_code_for_paper("2112.00337")
have("2112.00337")

Connect an agent — have() is free.