English
Related papers

Related papers: Two-step counterfactual generation for OOD example…

200 papers

The usage of deep neural networks in safety-critical systems is limited by our ability to guarantee their correct behavior. Runtime monitors are components aiming to identify unsafe predictions and discard them before they can lead to…

Machine Learning · Computer Science 2023-01-16 Joris Guérin , Kevin Delmas , Raul Sena Ferreira , Jérémie Guiochet

This paper presents a novel evaluation framework for Out-of-Distribution (OOD) detection that aims to assess the performance of machine learning models in more realistic settings. We observed that the real-world requirements for testing OOD…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Vahid Reza Khazaie , Anthony Wong , Mohammad Sabokrou

Out-of-distribution (OoD) inputs pose a persistent challenge to deep learning models, often triggering overconfident predictions on non-target objects. While prior work has primarily focused on refining scoring functions and adjusting…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Changshun Wu , Weicheng He , Chih-Hong Cheng , Xiaowei Huang , Saddek Bensalem

To understand the black-box characteristics of deep networks, counterfactual explanation that deduces not only the important features of an input space but also how those features should be modified to classify input as a target class has…

Machine Learning · Computer Science 2022-08-15 Hong-Gyu Jung , Sin-Han Kang , Hee-Dong Kim , Dong-Ok Won , Seong-Whan Lee

Distinguishing in- and out-of-distribution (OOD) inputs is crucial for reliable deployment of classification systems. However, OOD data is typically unavailable or difficult to collect, posing a significant challenge for accurate OOD…

Computation and Language · Computer Science 2025-10-03 Momin Abbas , Muneeza Azmat , Raya Horesh , Mikhail Yurochkin

When deploying machine learning models in high-stakes real-world environments such as health care, it is crucial to accurately assess the uncertainty concerning a model's prediction on abnormal inputs. However, there is a scarcity of…

Machine Learning · Computer Science 2020-11-20 Dennis Ulmer , Lotta Meijerink , Giovanni Cinà

Our goal is to perform out-of-distribution (OOD) detection, i.e., to detect when a robot is operating in environments drawn from a different distribution than the ones used to train the robot. We leverage Probably Approximately Correct…

Robotics · Computer Science 2023-11-08 Alec Farid , Sushant Veer , Divyanshu Pachisia , Anirudha Majumdar

Despite rapid advances in AI, safety remains the main bottleneck to deploying machine-learning systems. A critical safety component is out-of-distribution detection: given an input, decide whether it comes from the same distribution as the…

Machine Learning · Computer Science 2025-11-06 Joonas Järve , Karl Kaspar Haavel , Meelis Kull

The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples. Previous work applied recognition-based methods to learn the ID features, which tend to learn…

Computer Vision and Pattern Recognition · Computer Science 2023-04-12 Jingyao Li , Pengguang Chen , Shaozuo Yu , Zexin He , Shu Liu , Jiaya Jia

Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Hao Dong , Yue Zhao , Eleni Chatzi , Olga Fink

Whilst an abundance of techniques have recently been proposed to generate counterfactual explanations for the predictions of opaque black-box systems, markedly less attention has been paid to exploring the uncertainty of these generated…

Machine Learning · Computer Science 2021-07-22 Eoin Delaney , Derek Greene , Mark T. Keane

A key feature of out-of-distribution (OOD) detection is to exploit a trained neural network by extracting statistical patterns and relationships through the multi-layer classifier to detect shifts in the expected input data distribution.…

Machine Learning · Computer Science 2023-06-07 Eduardo Dadalto , Pierre Colombo , Guillaume Staerman , Nathan Noiry , Pablo Piantanida

Recently, a groundswell of research has identified the use of counterfactual explanations as a potentially significant solution to the Explainable AI (XAI) problem. It is argued that (a) technically, these counterfactual cases can be…

Artificial Intelligence · Computer Science 2020-05-29 Mark T. Keane , Barry Smyth

A serious problem in image classification is that a trained model might perform well for input data that originates from the same distribution as the data available for model training, but performs much worse for out-of-distribution (OOD)…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Rajat Koner , Poulami Sinhamahapatra , Karsten Roscher , Stephan Günnemann , Volker Tresp

Counterfactual explanations are one of the most popular methods to make predictions of black box machine learning models interpretable by providing explanations in the form of `what-if scenarios'. Most current approaches optimize a…

Machine Learning · Statistics 2020-10-16 Susanne Dandl , Christoph Molnar , Martin Binder , Bernd Bischl

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

Machine Learning · Computer Science 2021-06-07 Robert-Florian Samoilescu , Arnaud Van Looveren , Janis Klaise

Ensuring transparency in AI decision-making requires interpretable explanations, particularly at the instance level. Counterfactual explanations are a powerful tool for this purpose, but existing techniques frequently depend on synthetic…

Machine Learning · Computer Science 2025-02-13 Minh Hieu Nguyen , Viet Hung Doan , Anh Tuan Nguyen , Jun Jo , Quoc Viet Hung Nguyen

Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Kirill Sirotkin , Marcos Escudero-Viñolo , Pablo Carballeira , Mayug Maniparambil , Catarina Barata , Noel E. O'Connor

Machine learning models are prone to making incorrect predictions on inputs that are far from the training distribution. This hinders their deployment in safety-critical applications such as autonomous vehicles and healthcare. The detection…

Machine Learning · Computer Science 2022-07-26 Ramneet Kaur , Kaustubh Sridhar , Sangdon Park , Susmit Jha , Anirban Roy , Oleg Sokolsky , Insup Lee

Out-of-distribution (OOD) detection is a crucial task for ensuring the reliability and safety of deep learning. Currently, discriminator models outperform other methods in this regard. However, the feature extraction process used by…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Luping Liu , Yi Ren , Xize Cheng , Rongjie Huang , Chongxuan Li , Zhou Zhao