English
Related papers

Related papers: A margin-based replacement for cross-entropy loss

200 papers

Class imbalance and the difficulty imbalance are the two types of data imbalance that affect the performance of neural networks in medical segmentation tasks. In class imbalance the loss is dominated by the majority classes and in…

Image and Video Processing · Electrical Eng. & Systems 2025-06-23 Seyed Mohsen Hosseini

Neural networks are trained by minimizing a loss function that defines the discrepancy between the predicted model output and the target value. The selection of the loss function is crucial to achieve task-specific behaviour and highly…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Shakhnaz Akhmedova , Nils Körber

In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can be exacerbated by overfitting due to the minimization of the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Bingyuan Liu , Ismail Ben Ayed , Adrian Galdran , Jose Dolz

Up-to-date sea ice charts are crucial for safer navigation in ice-infested waters. Recently, Convolutional Neural Network (CNN) models show the potential to accelerate the generation of ice maps for large regions. However, results from CNN…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Rafael Pires de Lima , Behzad Vahedi , Morteza Karimzadeh

Both generative learning and discriminative learning have recently witnessed remarkable progress using Deep Neural Networks (DNNs). For structured input synthesis and structured output prediction problems (e.g., layout-to-image synthesis…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Wei Sun , Tianfu Wu

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Aritra Ghosh , Andrew Lan

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

Deep learning has achieved remarkable success in graph-related tasks, yet this accomplishment heavily relies on large-scale high-quality annotated datasets. However, acquiring such datasets can be cost-prohibitive, leading to the practical…

Machine Learning · Computer Science 2024-03-11 Ling-Hao Chen , Yuanshuo Zhang , Taohua Huang , Liangcai Su , Zeyi Lin , Xi Xiao , Xiaobo Xia , Tongliang Liu

Entropy-based deep reasoning has emerged as a promising direction for improving the reasoning capabilities of Large Language Models (LLMs), but existing methods often either increase response length indiscriminately or shorten responses at…

Computation and Language · Computer Science 2026-05-20 Shuyu Wei , Jian Sun , Delai Qiu , Yining Wang , Shengping Liu , Jiaen Liang , Ying Fu , Wei Huang , Jitao Sang

Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly outnumber positive examples, and the huge number of background examples (or easy-negative…

Computation and Language · Computer Science 2020-09-01 Xiaoya Li , Xiaofei Sun , Yuxian Meng , Junjun Liang , Fei Wu , Jiwei Li

As world knowledge advances and new task schemas emerge, Continual Learning (CL) becomes essential for keeping Large Language Models (LLMs) current and addressing their shortcomings. This process typically involves continual instruction…

Machine Learning · Computer Science 2024-12-17 Haokun Zhao , Haixia Han , Jie Shi , Chengyu Du , Jiaqing Liang , Yanghua Xiao

Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source,…

Image and Video Processing · Electrical Eng. & Systems 2021-11-16 Sivaramakrishnan Rajaraman , Ghada Zamzmi , Sameer Antani

Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e.g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models. Since collecting new training…

Machine Learning · Computer Science 2020-02-21 Tianyu Pang , Kun Xu , Yinpeng Dong , Chao Du , Ning Chen , Jun Zhu

In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree expressing the inclusion of classes in superclasses. We introduce a loss for this type of supervised hierarchical…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Nicolas Urbani , Sylvain Rousseau , Yves Grandvalet , Leonardo Tanzi

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

Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such a memorization issue in the presence of label noise. From the fact that deep neural networks cannot generalize to neighborhoods of…

Machine Learning · Computer Science 2020-11-12 Jisoo Lee , Sae-Young Chung

As shown in recent research, deep neural networks can perfectly fit randomly labeled data, but with very poor accuracy on held out data. This phenomenon indicates that loss functions such as cross-entropy are not a reliable indicator of…

Machine Learning · Statistics 2019-06-13 Yiding Jiang , Dilip Krishnan , Hossein Mobahi , Samy Bengio

An algorithm is proposed for solving optimization problems arising in neural network training for supervised learning. The unique feature of the algorithm is the use of an auxiliary loss, in addition to the original loss employed for model…

Optimization and Control · Mathematics 2026-05-11 Yunlang Zhu , Lingjun Guo , Zahra Khatti , Xiaoyi Qu , Chia-Yuan Wu , Lara Zebiane , Frank E. Curtis

Beam search is a desirable choice of test-time decoding algorithm for neural sequence models because it potentially avoids search errors made by simpler greedy methods. However, typical cross entropy training procedures for these models do…

Machine Learning · Computer Science 2017-10-10 Kartik Goyal , Graham Neubig , Chris Dyer , Taylor Berg-Kirkpatrick

Mean square error (MSE) has been the preferred choice as loss function in the current deep neural network (DNN) based speech separation techniques. In this paper, we propose a new cost function with the aim of optimizing the extended short…

Sound · Computer Science 2018-07-19 Gaurav Naithani , Joonas Nikunen , Lars Bramsløw , Tuomas Virtanen