English
Related papers

Related papers: Trade-offs in Top-k Classification Accuracies on L…

200 papers

The cross-entropy softmax loss is the primary loss function used to train deep neural networks. On the other hand, the focal loss function has been demonstrated to provide improved performance when there is an imbalance in the number of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Leslie N. Smith

To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis…

Machine Learning · Computer Science 2026-01-05 Waqas Ahmed , Sheeba Samuel , Kevin Coakley , Birgitta Koenig-Ries , Odd Erik Gundersen

Current deep learning solutions are well known for not informing whether they can reliably classify an example during inference. One of the most effective ways to build more reliable deep learning solutions is to improve their performance…

Machine Learning · Computer Science 2022-08-09 David Macêdo

Modern deep learning based classifiers show very high accuracy on test data but this does not provide sufficient guarantees for safe deployment, especially in high-stake AI applications such as medical diagnosis. Usually, predictions are…

Machine Learning · Computer Science 2022-05-09 David Stutz , Krishnamurthy , Dvijotham , Ali Taylan Cemgil , Arnaud Doucet

There is no such thing as a perfect dataset. In some datasets, deep neural networks discover underlying heuristics that allow them to take shortcuts in the learning process, resulting in poor generalization capability. Instead of using…

Computation and Language · Computer Science 2022-11-28 Frano Rajič , Ivan Stresec , Axel Marmet , Tim Poštuvan

We study the problem of improving the performance of online algorithms by incorporating machine-learned predictions. The goal is to design algorithms that are both consistent and robust, meaning that the algorithm performs well when…

Machine Learning · Computer Science 2020-10-23 Alexander Wei , Fred Zhang

Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class similarity nor inter-class margin of the learned deep…

Computer Vision and Pattern Recognition · Computer Science 2017-12-06 José Lezama , Qiang Qiu , Pablo Musé , Guillermo Sapiro

In this paper, we study the problem of fair classification in the presence of prior probability shifts, where the training set distribution differs from the test set. This phenomenon can be observed in the yearly records of several…

Machine Learning · Computer Science 2020-05-08 Arpita Biswas , Suvam Mukherjee

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…

Computer Vision and Pattern Recognition · Computer Science 2021-03-29 Peng Wang , Kai Han , Xiu-Shen Wei , Lei Zhang , Lei Wang

Deep neural networks (DNNs) often suffer from the overconfidence issue, where incorrect predictions are made with high confidence scores, hindering the applications in critical systems. In this paper, we propose a novel approach called…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Yijun Liu , Jiequan Cui , Zhuotao Tian , Senqiao Yang , Qingdong He , Xiaoling Wang , Jingyong Su

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks…

Machine Learning · Computer Science 2024-06-10 Yu-Chang Wu , Shen-Huan Lyu , Haopu Shang , Xiangyu Wang , Chao Qian

Calibration allows predictions to be reliably interpreted as probabilities by decision makers. We propose a decision-theoretic calibration error, the Calibration Decision Loss (CDL), defined as the maximum improvement in decision payoff…

Machine Learning · Computer Science 2024-10-14 Lunjia Hu , Yifan Wu

Deep neural network models degrade significantly in the long-tailed data distribution, with the overall training data dominated by a small set of classes in the head, and the tail classes obtaining less training examples. Addressing the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Brainard Philemon Jagati , Jitendra Tembhurne , Harsh Goud , Rudra Pratap Singh , Chandrashekhar Meshram

We provide a general framework for characterizing the trade-off between accuracy and robustness in supervised learning. We propose a method and define quantities to characterize the trade-off between accuracy and robustness for a given…

Machine Learning · Computer Science 2025-05-26 Zhun Deng , Cynthia Dwork , Jialiang Wang , Yao Zhao

Graphical models have gained a lot of attention recently as a tool for learning and representing dependencies among variables in multivariate data. Often, domain scientists are looking specifically for differences among the dependency…

Machine Learning · Statistics 2013-07-11 Diane Oyen , Alexandru Niculescu-Mizil , Rachel Ostroff , Alex Stewart , Vincent P. Clark

Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. This…

Machine Learning · Computer Science 2019-01-29 Hassan Ismail Fawaz , Germain Forestier , Jonathan Weber , Lhassane Idoumghar , Pierre-Alain Muller

We introduce a novel loss function for training deep learning architectures to perform classification. It consists in minimizing the smoothness of label signals on similarity graphs built at the output of the architecture. Equivalently, it…

Machine Learning · Computer Science 2019-05-02 Myriam Bontonou , Carlos Lassance , Ghouthi Boukli Hacene , Vincent Gripon , Jian Tang , Antonio Ortega

We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited synthetic prediction-label pairs, without accessing real samples during the main loss…

Machine Learning · Computer Science 2026-05-06 Meng Xiang , Yan Pei

Modern neural architectures for classification tasks are trained using the cross-entropy loss, which is widely believed to be empirically superior to the square loss. In this work we provide evidence indicating that this belief may not be…

Machine Learning · Computer Science 2021-10-26 Like Hui , Mikhail Belkin

We consider the use of machine learning for hypothesis testing with an emphasis on target detection. Classical model-based solutions rely on comparing likelihoods. These are sensitive to imperfect models and are often computationally…

Machine Learning · Computer Science 2022-06-14 Tzvi Diskin , Uri Okun , Ami Wiesel