paper-with-me

홈 › Papers

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation

2023-06-01 · Julian Bitterwolf, Maximilian Müller, Matthias Hein

Out-of-distribution (OOD) detection is the problem of identifying inputs which are unrelated to the in-distribution task. The OOD detection performance when the in-distribution (ID) is ImageNet-1K is commonly being tested on a small range of test OOD datasets. We find that most of the currently used test OOD datasets, including datasets from the open set recognition (OSR) literature, have severe issues: In some cases more than 50$\%$ of the dataset contains objects belonging to one of the ID classes. These erroneous samples heavily distort the evaluation of OOD detectors. As a solution, we introduce with NINCO a novel test OOD dataset, each sample checked to be ID free, which with its fine-grained range of OOD classes allows for a detailed analysis of an OOD detector's strengths and failure modes, particularly when paired with a number of synthetic "OOD unit-tests". We provide detailed evaluations across a large set of architectures and OOD detection methods on NINCO and the unit-tests, revealing new insights about model weaknesses and the effects of pretraining on OOD detection performance. We provide code and data at https://github.com/j-cb/NINCO.

📄 PDF Abstract BibTeX arXiv:2306.00826

Code (2)

j-cb/ninco 공식 구현 pytorch
robertsi20/Conceptualizing-Uncertainty pytorch

Tasks

Open Set LearningOut-of-Distribution DetectionOut of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection

2026-01-15 · Gerhard Krumpl, Henning Avenhaus, Horst Possegger arxiv

Out-of-distribution (OOD) detection is crucial for deploying robust and reliable machine-learning systems in open-world settings. Despite steady advances in OOD detectors, their interplay with modern training pipelines t…

Out-of-Distribution Detection

Overcoming Label Ambiguity with Multi-label Iterated Learning

2021-09-29 · Sai Rajeswar Mudumba, Pau Rodriguez, Soumye Singhal, David Vazquez 외

Transfer learning from ImageNet pre-trained models has become essential for many computer vision tasks. Recent studies have shown that ImageNet includes label ambiguity, where images with multiple object classes present …

Multi-Label LearningTransfer Learning

Can Biases in ImageNet Models Explain Generalization?

2024-04-01 · CVPR 2024 1 · Paul Gavrikov, Janis Keuper

The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current …

image-classificationImage Classification

Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study

2026-05-13 · Nils Loose, Joseph Bienhüls, Kristoffer Hempel, Felix Mächtle 외 arxiv

Automated detection of vulnerability-fixing commits (VFCs) is critical for timely security patch deployment, as advisory databases lag patch releases by a median of 25 days and many fixes never receive advisories. We pre…

ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms

2023-10-03 · William Yang, Byron Zhang, Olga Russakovsky

The task of out-of-distribution (OOD) detection is notoriously ill-defined. Earlier works focused on new-class detection, aiming to identify label-altering data distribution shifts, also known as "semantic shift." Howeve…

Out-of-Distribution DetectionOut of Distribution (OOD) DetectionSemantic Shift Detection