English
Related papers

Related papers: Maintaining Difficulty: A Margin Scheduler for Tri…

200 papers

Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions. When combined with the common practice…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Qin Zhang , Linghan Xu , Qingming Tang , Jun Fang , Ying Nian Wu , Joe Tighe , Yifan Xing

Machine Learning~(ML) has provided promising results in recent years across different applications and domains. However, in many cases, qualities such as reliability or even safety need to be ensured. To this end, one important aspect is to…

The loss function used to train a neural network is strongly connected to its output layer from a statistical point of view. This technical report analyzes common activation functions for a neural network output layer, like linear, sigmoid,…

Machine Learning · Computer Science 2025-11-10 Fernando Berzal

In deep learning, auxiliary training has been widely used to assist the training of models. During the training phase, using auxiliary modules to assist training can improve the performance of the model. During the testing phase, auxiliary…

Artificial Intelligence · Computer Science 2022-05-30 Wenrui Gan , Zhulin Liu , C. L. Philip Chen , Tong Zhang

Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations such as pose, illumination, viewpoint, background, and sensor noise. Recent approaches…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Sinan Sabri , Zaigham Randhawa , Gianfranco Doretto

This paper introduces a new loss function, OSM (One-Sided Margin), to solve maximum-margin classification problems effectively. Unlike the hinge loss, in OSM the margin is explicitly determined with corresponding hyperparameters and then…

Machine Learning · Computer Science 2022-06-03 Ali Karimi , Zahra Mousavi Kouzehkanan , Reshad Hosseini , Hadi Asheri

Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship. It is critical in many machine learning, pattern recognition and data mining algorithms, and usually require large amount of label…

Machine Learning · Statistics 2018-11-13 Yong Luo , Yonggang Wen , Ling-Yu Duan , Dacheng Tao

Deep learning has been successfully applied to human activity recognition. However, training deep neural networks requires explicitly labeled data which is difficult to acquire. In this paper, we present a model with multiple siamese…

Human-Computer Interaction · Computer Science 2023-07-19 Taoran Sheng , Manfred Huber

In this paper, we study the implicit regularization of the gradient descent algorithm in homogeneous neural networks, including fully-connected and convolutional neural networks with ReLU or LeakyReLU activations. In particular, we study…

Machine Learning · Computer Science 2021-01-01 Kaifeng Lyu , Jian Li

Deep Learning (DL) methods show very good performance when trained on large, balanced data sets. However, many practical problems involve imbalanced data sets, or/and classes with a small number of training samples. The performance of DL…

Machine Learning · Computer Science 2017-02-07 Dolev Raviv , Margarita Osadchy

We study adversarial robustness of neural networks from a margin maximization perspective, where margins are defined as the distances from inputs to a classifier's decision boundary. Our study shows that maximizing margins can be achieved…

Machine Learning · Computer Science 2020-03-06 Gavin Weiguang Ding , Yash Sharma , Kry Yik Chau Lui , Ruitong Huang

Minimizing inconsistencies across successive versions of an AI system is as crucial as reducing the overall error. In image classification, such inconsistencies manifest as negative flips, where an updated model misclassifies test samples…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Simone Ricci , Niccolò Biondi , Federico Pernici , Alberto Del Bimbo

Boosting techniques and neural networks are particularly effective machine learning methods for insurance pricing. Often in practice, there are nevertheless endless debates about the choice of the right loss function to be used to train the…

Machine Learning · Statistics 2021-07-12 Michel Denuit , Arthur Charpentier , Julien Trufin

The deep metric learning (DML) objective is to learn a neural network that maps into an embedding space where similar data are near and dissimilar data are far. However, conventional proxy-based losses for DML have two problems: gradient…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Shozo Saeki , Minoru Kawahara , Hirohisa Aman

The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images. While deep metric learning has yielded impressive…

Computer Vision and Pattern Recognition · Computer Science 2017-08-08 Jian Wang , Feng Zhou , Shilei Wen , Xiao Liu , Yuanqing Lin

Preference are central to decision making by both machines and humans. Representing, learning, and reasoning with preferences is an important area of study both within computer science and across the sciences. When working with preferences…

Machine Learning · Computer Science 2020-10-15 Andrea Loreggia , Nicholas Mattei , Francesca Rossi , K. Brent Venable

The problem of distance metric learning is mostly considered from the perspective of learning an embedding space, where the distances between pairs of examples are in correspondence with a similarity metric. With the rise and success of…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Yehao Li , Ting Yao , Yingwei Pan , Hongyang Chao , Tao Mei

Deep neural networks often exhibit substantial disparities in class-wise accuracy, even when trained on class-balanced data, posing concerns for reliable deployment. While prior efforts have explored empirical remedies, a theoretical…

Machine Learning · Computer Science 2026-02-03 Beier Zhu , Kesen Zhao , Jiequan Cui , Qianru Sun , Yuan Zhou , Xun Yang , Hanwang Zhang

Neural networks trained under different hyperparameter settings can fall into distinct training "regimes," with consistent behavior within regimes and qualitative differences across regimes. In this paper, we study such multi-regime…

Machine Learning · Computer Science 2026-05-29 Yuxin Wang , Yuanzhe Hu , Xiaokun Zhong , Xiaopeng Wang , Haiquan Lu , Tianyu Pang , Michael W. Mahoney , Yujun Yan , Pu Ren , Yaoqing Yang

We present a selective sampling method designed to accelerate the training of deep neural networks. To this end, we introduce a novel measurement, the minimal margin score (MMS), which measures the minimal amount of displacement an input…

Machine Learning · Computer Science 2019-11-19 Berry Weinstein , Shai Fine , Yacov Hel-Or
‹ Prev 1 3 4 5 6 7 10 Next ›