English
Related papers

Related papers: Understanding Softmax Confidence and Uncertainty

200 papers

Question answering (QA) models are shown to be insensitive to large perturbations to inputs; that is, they make correct and confident predictions even when given largely perturbed inputs from which humans can not correctly derive answers.…

Computation and Language · Computer Science 2022-11-30 Kazutoshi Shinoda , Saku Sugawara , Akiko Aizawa

Loss functions play a key role in training superior deep neural networks. In convolutional neural networks (CNNs), the popular cross entropy loss together with softmax does not explicitly guarantee minimization of intra-class variance or…

Computer Vision and Pattern Recognition · Computer Science 2019-04-26 XiaoBin Li , WeiQiang Wang

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler…

Machine Learning · Computer Science 2021-07-07 Marcel Keller , Ke Sun

Soft labeling becomes a common output regularization for generalization and model compression of deep neural networks. However, the effect of soft labeling on out-of-distribution (OOD) detection, which is an important topic of machine…

Machine Learning · Computer Science 2020-07-08 Doyup Lee , Yeongjae Cheon

Data has now become a shortcoming of deep learning. Researchers in their own fields share the thinking that "deep neural networks might not always perform better when they eat more data," which still lacks experimental validation and a…

Machine Learning · Computer Science 2022-05-31 Jiachen Yang , Zhuo Zhang , Yicheng Gong , Shukun Ma , Xiaolan Guo , Yue Yang , Shuai Xiao , Jiabao Wen , Yang Li , Xinbo Gao , Wen Lu , Qinggang Meng

Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution…

Machine Learning · Computer Science 2022-09-13 Damien Teney , Ehsan Abbasnejad , Simon Lucey , Anton van den Hengel

Improving the accuracy of deep neural networks (DNNs) on out-of-distribution (OOD) data is critical to an acceptance of deep learning (DL) in real world applications. It has been observed that accuracies on in-distribution (ID) versus OOD…

Machine Learning · Computer Science 2022-07-12 Sara Fridovich-Keil , Brian R. Bartoldson , James Diffenderfer , Bhavya Kailkhura , Peer-Timo Bremer

Deep Neural Networks (DNNs) have performed admirably in classification tasks. However, the characterization of their classification uncertainties, required for certain applications, has been lacking. In this work, we investigate the issue…

Machine Learning · Computer Science 2023-11-28 Yu Pan , Kwo-Sen Kuo , Michael L. Rilee , Hongfeng Yu

The inability of artificial neural networks to assess the uncertainty of their predictions is an impediment to their widespread use. We distinguish two types of learnable uncertainty: model uncertainty due to a lack of training data and…

Machine Learning · Computer Science 2022-06-14 Hans Weytjens , Jochen De Weerdt

In satellite image analysis, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data and differences in the geographic area. Deep learning based models may…

Machine Learning · Computer Science 2021-04-13 Jakob Gawlikowski , Sudipan Saha , Anna Kruspe , Xiao Xiang Zhu

The question whether inputs are valid for the problem a neural network is trying to solve has sparked interest in out-of-distribution (OOD) detection. It is widely assumed that Bayesian neural networks (BNNs) are well suited for this task,…

Machine Learning · Computer Science 2022-02-22 Francesco D'Angelo , Christian Henning

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Antonio Loquercio , Mattia Segù , Davide Scaramuzza

Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation and hallucination detection, motivating a growing interest in efficient probe-based approaches. Yet it remains unclear…

Computation and Language · Computer Science 2026-04-14 Joe Stacey , Hadas Orgad , Kentaro Inui , Benjamin Heinzerling , Nafise Sadat Moosavi

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

Estimated density is often interpreted as indicating how typical a sample is under a model. Yet deep models trained on one dataset can assign higher density to simpler out-of-distribution (OOD) data than to in-distribution test data. We…

Machine Learning · Computer Science 2026-04-03 Weyl Lu , Chenjie Hao , Yubei Chen

The easiness at which adversarial instances can be generated in deep neural networks raises some fundamental questions on their functioning and concerns on their use in critical systems. In this paper, we draw a connection between…

Machine Learning · Computer Science 2018-03-02 Mahdieh Abbasi , Christian Gagné

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…

Machine Learning · Computer Science 2018-02-14 Angus Galloway , Graham W. Taylor , Medhat Moussa

It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted, a challenge known as out-of-distribution (OOD) detection. For neural networks, one approach to this task…

Reliable use of deep neural networks (DNNs) for medical image analysis requires methods to identify inputs that differ significantly from the training data, called out-of-distribution (OOD), to prevent erroneous predictions. OOD detection…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Harry Anthony , Konstantinos Kamnitsas

Prediction under uncertainty is a critical requirement for the deep neural network to succeed responsibly. This paper focuses on selective prediction, which allows DNNs to make informed decisions about when to predict or abstain based on…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Ishan Mishra , Jiajie Li , Deepak Mishra , Jinjun Xiong
‹ Prev 1 3 4 5 6 7 10 Next ›