Papers › An Effective Baseline for Robustness to Distributional Shift

An Effective Baseline for Robustness to Distributional Shift

15 May 2021arXiv:2105.07107archive 2025-07-28

Sunil Thulasidasan, Sushil Thapa, Sayera Dhaubhadel, Gopinath Chennupati, Tanmoy Bhattacharya, Jeff Bilmes

Refraining from confidently predicting when faced with categories of inputs different from those seen during training is an important requirement for the safe deployment of deep learning systems. While simple to state, this has been a particularly challenging problem in deep learning, where models often end up making overconfident predictions in such situations. In this work we present a simple, but highly effective approach to deal with out-of-distribution detection that uses the principle of abstention: when encountering a sample from an unseen class, the desired behavior is to abstain from predicting. Our approach uses a network with an extra abstention class and is trained on a dataset that is augmented with an uncurated set that consists of a large number of out-of-distribution (OoD) samples that are assigned the label of the abstention class; the model is then trained to learn an effective discriminator between in and out-of-distribution samples. We compare this relatively simple approach against a wide variety of more complex methods that have been proposed both for out-of-distribution detection as well as uncertainty modeling in deep learning, and empirically demonstrate its effectiveness on a wide variety of of benchmarks and deep architectures for image recognition and text classification, often outperforming existing approaches by significant margins. Given the simplicity and effectiveness of this method, we propose that this approach be used as a new additional baseline for future work in this domain.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Sushil-Thapa/Abstention-OoD officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep LearningOut-of-Distribution DetectionRobust classificationtext-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection 20 Newsgroups 2-Layered GRU AUROC 99.6 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection 20 Newsgroups 2-Layered GRU FPR95 1.78 #1 of 2 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 Wide ResNet 40x2 AUROC 99.9 #2 of 10 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 Wide ResNet 40x2 FPR95 2.0 #2 of 10 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 Wide ResNet 40x2 AUROC 97.7 #1 of 4 Archive leaderboard report
Out-of-Distribution Detection CIFAR-100 Wide ResNet 40x2 FPR95 23.4 #1 of 4 Archive leaderboard report
Out-of-Distribution Detection SST 2-Layered GRU AUROC 99.7 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection SST 2-Layered GRU FPR95 20.9 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection TREC-NEWS 2-Layered GRU AUROC 99.9 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection TREC-NEWS 2-Layered GRU FPR95 4.7 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Average PoolingBatch NormalizationConvolutionDropoutGRUGlobal Average PoolingKaiming InitializationReLUResidual ConnectionWide Residual BlockWideResNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections