English
Related papers

Related papers: The Devil is in the Margin: Margin-based Label Smo…

200 papers

The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i.e., the model tends to classify tail classes as head classes.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Yidong Wang , Bowen Zhang , Wenxin Hou , Zhen Wu , Jindong Wang , Takahiro Shinozaki

The generalization and learning speed of a multi-class neural network can often be significantly improved by using soft targets that are a weighted average of the hard targets and the uniform distribution over labels. Smoothing the labels…

Machine Learning · Computer Science 2020-06-12 Rafael Müller , Simon Kornblith , Geoffrey Hinton

Neural networks are not learning optimal decision boundaries. We show that decision boundaries are situated in areas of low training data density. They are impacted by few training samples which can easily lead to overfitting. We provide a…

Machine Learning · Computer Science 2023-10-09 Johannes Schneider

In this paper, we show that although the minimizers of cross-entropy and related classification losses are off at infinity, network weights learned by gradient flow converge in direction, with an immediate corollary that network…

Machine Learning · Computer Science 2020-10-27 Ziwei Ji , Matus Telgarsky

To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the…

Machine Learning · Computer Science 2021-06-03 Xinshao Wang , Yang Hua , Elyor Kodirov , David A. Clifton , Neil M. Robertson

We study the classical binary classification problem for hypothesis spaces of Deep Neural Networks (DNNs) under Tsybakov's low-noise condition with exponent $q>0$, as well as its limit case $q=\infty$, which we refer to as the \emph{hard…

Machine Learning · Computer Science 2026-05-06 Nathanael Tepakbong , Xiang Zhou , Ding-Xuan Zhou

As one of the most exciting features of large language models (LLMs), in-context learning is a mixed blessing. While it allows users to fast-prototype a task solver with only a few training examples, the performance is generally sensitive…

Computation and Language · Computer Science 2023-10-17 Zhongtao Jiang , Yuanzhe Zhang , Cao Liu , Jun Zhao , Kang Liu

We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…

Machine Learning · Computer Science 2020-10-01 Lang Huang , Chao Zhang , Hongyang Zhang

Regularization is essential for avoiding over-fitting to training data in network optimization, leading to better generalization of the trained networks. The label noise provides a strong implicit regularization by replacing the target…

Machine Learning · Computer Science 2022-05-04 Kensuke Nakamura , Bong-Soo Sohn , Kyoung-Jae Won , Byung-Woo Hong

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

Detecting out-of-distribution inputs is critical for safe deployment of machine learning models in the real world. However, neural networks are known to suffer from the overconfidence issue, where they produce abnormally high confidence for…

Machine Learning · Computer Science 2022-06-27 Hongxin Wei , Renchunzi Xie , Hao Cheng , Lei Feng , Bo An , Yixuan Li

Classifiers often learn to be biased corresponding to the class-imbalanced dataset, especially under the semi-supervised learning (SSL) set. While previous work tries to appropriately re-balance the classifiers by subtracting a…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Weiwei Xing , Yue Cheng , Hongzhu Yi , Xiaohui Gao , Xiang Wei , Xiaoyu Guo , Yuming Zhang , Xinyu Pang

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been…

Recent works have shown that deep metric learning algorithms can benefit from weak supervision from another input modality. This additional modality can be incorporated directly into the popular triplet-based loss function as distances.…

Computer Vision and Pattern Recognition · Computer Science 2020-06-29 Istvan Fehervari , Ives Macedo

Introduced as a notion of algorithmic fairness, multicalibration has proved to be a powerful and versatile concept with implications far beyond its original intent. This stringent notion -- that predictions be well-calibrated across a rich…

Machine Learning · Computer Science 2022-06-17 Parikshit Gopalan , Michael P. Kim , Mihir Singhal , Shengjia Zhao

Neural network prediction probabilities and accuracy are often only weakly-correlated. Inherent label ambiguity in training data for image segmentation aggravates such miscalibration. We show that logit consistency across stochastic…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Neerav Karani , Neel Dey , Polina Golland

Recent work has shown that language models' (LMs) prompt-based learning capabilities make them well suited for automating data labeling in domains where manual annotation is expensive. The challenge is that while writing an initial prompt…

Machine Learning · Computer Science 2023-07-21 Neel Guha , Mayee F. Chen , Kush Bhatia , Azalia Mirhoseini , Frederic Sala , Christopher Ré

The design of complex engineering systems leads to solving very large optimization problems involving different disciplines. Strategies allowing disciplines to optimize in parallel by providing sub-objectives and splitting the problem into…

Machine Learning · Computer Science 2021-06-14 Jean de Becdelievre , Ilan Kroo

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…

Machine Learning · Computer Science 2022-10-26 Dongkyu Lee , Ka Chun Cheung , Nevin L. Zhang