English
Related papers

Related papers: Understanding Softmax Confidence and Uncertainty

200 papers

The need to avoid confident predictions on unfamiliar data has sparked interest in out-of-distribution (OOD) detection. It is widely assumed that Bayesian neural networks (BNN) are well suited for this task, as the endowed epistemic…

Machine Learning · Computer Science 2021-07-27 Christian Henning , Francesco D'Angelo , Benjamin F. Grewe

Out-of-distribution (OOD) detection is critical for preventing deep learning models from making incorrect predictions to ensure the safety of artificial intelligence systems. Especially in safety-critical applications such as medical…

Machine Learning · Computer Science 2023-02-16 Mouxiao Huang , Yu Qiao

We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test…

Machine Learning · Computer Science 2026-01-28 Maksim Kazanskii , Artem Kasianov

Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be suboptimal in deep architectures, attributing this to an explicit low-rank bias from L2…

Machine Learning · Computer Science 2026-05-25 Connall Garrod , Jonathan P. Keating , Christos Thrampoulidis

There has long been debates on how we could interpret neural networks and understand the decisions our models make. Specifically, why deep neural networks tend to be error-prone when dealing with samples that output low softmax scores. We…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Simiao Zuo , Jialin Wu

A key property of reasoning systems is the ability to make sharp decisions on their input data. For contemporary AI systems, a key carrier of sharp behaviour is the softmax function, with its capability to perform differentiable query-key…

Machine Learning · Computer Science 2025-06-03 Petar Veličković , Christos Perivolaropoulos , Federico Barbero , Razvan Pascanu

Simplicity bias, the propensity of deep models to over-rely on simple features, has been identified as a potential reason for limited out-of-distribution generalization of neural networks (Shah et al., 2020). Despite the important…

Machine Learning · Statistics 2024-11-08 Nikita Tsoy , Nikola Konstantinov

Deep neural networks have been successful in diverse discriminative classification tasks, although, they are poorly calibrated often assigning high probability to misclassified predictions. Potential consequences could lead to…

Machine Learning · Statistics 2020-10-06 John Mitros , Arjun Pakrashi , Brian Mac Namee

Evidential deep learning, built upon belief theory and subjective logic, offers a principled and computationally efficient way to turn a deterministic neural network uncertainty-aware. The resultant evidential models can quantify…

Machine Learning · Computer Science 2023-06-27 Deep Pandey , Qi Yu

Building robust deterministic neural networks remains a challenge. On the one hand, some approaches improve out-of-distribution detection at the cost of reducing classification accuracy in some situations. On the other hand, some methods…

Machine Learning · Computer Science 2022-08-09 David Macêdo , Cleber Zanchettin , Teresa Ludermir

Detecting deepfakes has become a critical challenge in Computer Vision and Artificial Intelligence. Despite significant progress in detection techniques, generalizing them to open-set scenarios continues to be a persistent difficulty.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Luca Maiano , Fabrizio Casadei , Irene Amerini

Confidence calibration is of great importance to the reliability of decisions made by machine learning systems. However, discriminative classifiers based on deep neural networks are often criticized for producing overconfident predictions…

Machine Learning · Computer Science 2021-08-17 Yezhen Wang , Bo Li , Tong Che , Kaiyang Zhou , Ziwei Liu , Dongsheng Li

Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Madhav Gupta , Vishak Prasad C , Ganesh Ramakrishnan

Out-of-distribution (OOD) detection is essential for model trustworthiness which aims to sensitively identify semantic OOD samples and robustly generalize for covariate-shifted OOD samples. However, we discover that the superior OOD…

Machine Learning · Computer Science 2024-10-16 Qingyang Zhang , Qiuxuan Feng , Joey Tianyi Zhou , Yatao Bian , Qinghua Hu , Changqing Zhang

Deep neural networks often face generalization problems to handle out-of-distribution (OOD) data, and there remains a notable theoretical gap between the contributing factors and their respective impacts. Literature evidence from…

Machine Learning · Computer Science 2024-04-24 Songming Zhang , Yuxiao Luo , Qizhou Wang , Haoang Chi , Xiaofeng Chen , Bo Han , Jinyan Li

Bayesian neural networks (BNNs), which estimate the full posterior distribution over model parameters, are well-known for their role in uncertainty quantification and its promising application in out-of-distribution detection (OoD). Amongst…

Machine Learning · Computer Science 2025-02-24 Kevin Raina

Neural networks (NNs) can achieved high performance in various fields such as computer vision, and natural language processing. However, deploying NNs in resource-constrained safety-critical systems has challenges due to uncertainty in the…

Machine Learning · Computer Science 2024-01-17 Soyed Tuhin Ahmed

Deep neural networks are powerful tools to detect hidden patterns in data and leverage them to make predictions, but they are not designed to understand uncertainty and estimate reliable probabilities. In particular, they tend to be…

Machine Learning · Statistics 2022-11-10 Bat-Sheva Einbinder , Yaniv Romano , Matteo Sesia , Yanfei Zhou

The ability to detect Out-of-Distribution (OOD) data is important in safety-critical applications of deep learning. The aim is to separate In-Distribution (ID) data drawn from the training distribution from OOD data using a measure of…

Machine Learning · Computer Science 2022-09-21 Guoxuan Xia , Christos-Savvas Bouganis

Recent advances in language modeling consist in pretraining highly parameterized neural networks on extremely large web-mined text corpora. Training and inference with such models can be costly in practice, which incentivizes the use of…

Computation and Language · Computer Science 2024-04-12 Nathan Godey , Éric de la Clergerie , Benoît Sagot