English
Related papers

Related papers: Taming the Cross Entropy Loss

200 papers

We introduce a new loss function TripleEntropy, to improve classification performance for fine-tuning general knowledge pre-trained language models based on cross-entropy and SoftTriple loss. This loss function can improve the robust…

Computation and Language · Computer Science 2022-11-28 Witold Sosnowski , Anna Wroblewska , Piotr Gawrysiak

Various tasks are reformulated as multi-label classification problems, in which the binary cross-entropy (BCE) loss is frequently utilized for optimizing well-designed models. However, the vanilla BCE loss cannot be tailored for diverse…

Machine Learning · Computer Science 2023-04-12 Yusheng Huang , Jiexing Qi , Xinbing Wang , Zhouhan Lin

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

Sequence-to-Sequence (Seq2Seq) models have achieved encouraging performance on the dialogue response generation task. However, existing Seq2Seq-based response generation methods suffer from a low-diversity problem: they frequently generate…

Information Retrieval · Computer Science 2019-02-26 Shaojie Jiang , Pengjie Ren , Christof Monz , Maarten de Rijke

We propose a novel loss function that dynamically rescales the cross entropy based on prediction difficulty regarding a sample. Deep neural network architectures in image classification tasks struggle to disambiguate visually similar…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Serim Ryou , Seong-Gyun Jeong , Pietro Perona

Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Yuchi Liu , Lei Wang , Yuli Zou , James Zou , Liang Zheng

Given two networks with the same training loss on a dataset, when would they have drastically different test losses and errors? Better understanding of this question of generalization may improve practical applications of deep networks. In…

Machine Learning · Computer Science 2018-07-26 Qianli Liao , Brando Miranda , Andrzej Banburski , Jack Hidary , Tomaso Poggio

The Improved Cross-Entropy (ICE) method is a powerful tool for estimating failure probabilities in reliability analysis. Its core idea is to approximate the optimal importance-sampling density by minimizing the forward Kullback-Leibler…

Numerical Analysis · Mathematics 2025-09-10 Zhiwei Gao , George Karniadakis

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Shihao Zhang , Linlin Yang , Michael Bi Mi , Xiaoxu Zheng , Angela Yao

The S{\o}rensen--Dice Coefficient has recently seen rising popularity as a loss function (also known as Dice loss) due to its robustness in tasks where the number of negative samples significantly exceeds that of positive samples, such as…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-05 Karn N. Watcharasupat , Thi Ngoc Tho Nguyen , Ngoc Khanh Nguyen , Zhen Jian Lee , Douglas L. Jones , Woon Seng Gan

Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of speech recognition compared with traditional autoregressive models. In this work, we present dynamic alignment…

Sound · Computer Science 2023-03-15 Xulong Zhang , Haobin Tang , Jianzong Wang , Ning Cheng , Jian Luo , Jing Xiao

The top-k error is a common measure of performance in machine learning and computer vision. In practice, top-k classification is typically performed with deep neural networks trained with the cross-entropy loss. Theoretical results indeed…

Machine Learning · Computer Science 2018-02-22 Leonard Berrada , Andrew Zisserman , M. Pawan Kumar

The training of ResNets and neural ODEs can be formulated and analyzed from the perspective of optimal control. This paper proposes a dissipative formulation of the training of ResNets and neural ODEs for classification problems by…

Machine Learning · Computer Science 2024-05-30 Jens Püttschneider , Timm Faulwasser

With the increasing complexity of the traffic environment, the significance of safety perception in intelligent driving is intensifying. Traditional methods in the field of intelligent driving perception rely on deep learning, which suffers…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Haobo Yang , Shiyan Zhang , Zhuoyi Yang , Xinyu Zhang , Jilong Guo , Zongyou Yang , Jun Li

In the context of adversarial robustness, a single model does not usually have enough power to defend against all possible adversarial attacks, and as a result, has sub-optimal robustness. Consequently, an emerging line of work has focused…

Machine Learning · Computer Science 2022-06-08 Dinghuai Zhang , Hongyang Zhang , Aaron Courville , Yoshua Bengio , Pradeep Ravikumar , Arun Sai Suggala

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

Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural networks. This paper studies label smoothing from the perspective of Neural Collapse (NC), a powerful empirical and theoretical framework which…

Machine Learning · Computer Science 2025-09-30 Li Guo , George Andriopoulos , Zifan Zhao , Shuyang Ling , Zixuan Dong , Keith Ross

State-of-the-art neural networks are vulnerable to adversarial examples; they can easily misclassify inputs that are imperceptibly different than their training and test data. In this work, we establish that the use of cross-entropy loss…

Machine Learning · Computer Science 2019-01-25 Kamil Nar , Orhan Ocal , S. Shankar Sastry , Kannan Ramchandran

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by…

Machine Learning · Computer Science 2019-08-08 Hao-Yun Chen , Jhao-Hong Liang , Shih-Chieh Chang , Jia-Yu Pan , Yu-Ting Chen , Wei Wei , Da-Cheng Juan

Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…

Machine Learning · Computer Science 2026-04-13 Matheus Vinícius Todescato , Joel Luís Carbonera