Papers › Outlier Exposure with Confidence Control for Out-of-Distribution Detection

Outlier Exposure with Confidence Control for Out-of-Distribution Detection

8 Jun 2019arXiv:1906.03509archive 2025-07-28

Aristotelis-Angelos Papadopoulos, Mohammad Reza Rajati, Nazim Shaikh, Jiamian Wang

Deep neural networks have achieved great success in classification tasks during the last years. However, one major problem to the path towards artificial intelligence is the inability of neural networks to accurately detect samples from novel class distributions and therefore, most of the existent classification algorithms assume that all classes are known prior to the training stage. In this work, we propose a methodology for training a neural network that allows it to efficiently detect out-of-distribution (OOD) examples without compromising much of its classification accuracy on the test examples from known classes. We propose a novel loss function that gives rise to a novel method, Outlier Exposure with Confidence Control (OECC), which achieves superior results in OOD detection with OE both on image and text classification tasks without requiring access to OOD samples. Additionally, we experimentally show that the combination of OECC with state-of-the-art post-training OOD detection methods, like the Mahalanobis Detector (MD) and the Gramian Matrices (GM) methods, further improves their performance in the OOD detection task, demonstrating the potential of combining training and post-training methods for OOD detection.

Paper PDF Code

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

Code

nazim1021/OOD-detection-using-OECC officialmentioned in papermentioned 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

Anomaly Detection Classification General Classification Image Classification Out of Distribution (OOD) Detection Out-of-Distribution Detection Text Classification text-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Out-of-Distribution Detection	20 Newsgroups	2-layer GRUs + OECC	AUROC	99.18	#2 of 2	Archive leaderboard	report
Out-of-Distribution Detection	CIFAR-10	ResNet 34 + OECC+GM	AUROC	99.7	#3 of 10	Archive leaderboard	report
Out-of-Distribution Detection	CIFAR-10 vs CIFAR-100	Wide 40-2 + OECC	AUPR	82.0	#9 of 14	Archive leaderboard	report
Out-of-Distribution Detection	CIFAR-10 vs CIFAR-100	Wide 40-2 + OECC	AUROC	94.9	#9 of 14	Archive leaderboard	report
Out-of-Distribution Detection	CIFAR-100	WRN 40-2 + OECC	FPR95	28.89	#2 of 4	Archive leaderboard	report
Out-of-Distribution Detection	CIFAR-100 vs CIFAR-10	WRN 40-2 + OECC	AUPR	35.2	#11 of 14	Archive leaderboard	report
Out-of-Distribution Detection	CIFAR-100 vs CIFAR-10	WRN 40-2 + OECC	AUROC	78.7	#11 of 14	Archive leaderboard	report
Out-of-Distribution Detection	CIFAR-100 vs SVHN	OECC + MD	AUROC	98.7	#1 of 5	Archive leaderboard	report
Out-of-Distribution Detection	ImageNet dogs vs ImageNet non-dogs	ResNet 34 + OE	AUROC	92.5	#2 of 3	Archive leaderboard	report
Out-of-Distribution Detection	MS-1M vs. IJB-C	ResNeXt 50 + OE	AUROC	52.6	#4 of 4	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 Pooling Batch Normalization Convolution Dropout Global Average Pooling Kaiming Initialization ReLU Residual Connection Wide Residual Block WideResNet

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