English
Related papers

Related papers: A Softmax-free Loss Function Based on Predefined O…

200 papers

In current practical face authentication systems, most face recognition (FR) algorithms are based on cosine similarity with softmax classification. Despite its reliable classification performance, this method struggles with hard samples. A…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Fan Xie , Yang Wang , Yikang Jiao , Zhenyu Yuan , Congxi Chen , Chuanxin Zhao

Traditional federated optimization methods perform poorly with heterogeneous data (ie, accuracy reduction), especially for highly skewed data. In this paper, we investigate the label distribution skew in FL, where the distribution of labels…

Machine Learning · Computer Science 2022-09-27 Jie Zhang , Zhiqi Li , Bo Li , Jianghe Xu , Shuang Wu , Shouhong Ding , Chao Wu

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

Cosine similarity is the common choice for measuring the distance between the feature representations in contrastive visual-textual alignment learning. However, empirically a learnable softmax temperature parameter is required when learning…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Zhun Sun

We propose a deep learning-based solution for the problem of feature learning in one-class classification. The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive features while…

Computer Vision and Pattern Recognition · Computer Science 2019-10-02 Pramuditha Perera , Vishal M. Patel

Deep-learning has proved in recent years to be a powerful tool for image analysis and is now widely used to segment both 2D and 3D medical images. Deep-learning segmentation frameworks rely not only on the choice of network architecture but…

Computer Vision and Pattern Recognition · Computer Science 2017-09-19 Carole H Sudre , Wenqi Li , Tom Vercauteren , Sébastien Ourselin , M. Jorge Cardoso

The current state-of-the-art decentralized learning algorithms mostly assume the data distribution to be Independent and Identically Distributed (IID). However, in practical scenarios, the distributed datasets can have significantly…

Machine Learning · Computer Science 2023-12-07 Sai Aparna Aketi , Kaushik Roy

In this paper, we propose a new deep neural network classifier that simultaneously maximizes the inter-class separation and minimizes the intra-class variation by using the polyhedral conic classification function. The proposed method has…

Computer Vision and Pattern Recognition · Computer Science 2021-02-26 Hakan Cevikalp , Bedirhan Uzun , Okan Köpüklü , Gurkan Ozturk

As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms.…

Machine Learning · Computer Science 2018-09-12 Apoorv Vyas , Nataraj Jammalamadaka , Xia Zhu , Dipankar Das , Bharat Kaul , Theodore L. Willke

The loss function is a key component in deep learning models. A commonly used loss function for classification is the cross entropy loss, which is a simple yet effective application of information theory for classification problems. Based…

Computer Vision and Pattern Recognition · Computer Science 2020-10-13 Zeyu Song , Dongliang Chang , Zhanyu Ma , Xiaoxu Li , Zheng-Hua Tan

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 this work we study loss functions for learning and evaluating probability distributions over large discrete domains. Unlike classification or regression where a wide variety of loss functions are used, in the distribution learning and…

Machine Learning · Computer Science 2019-08-05 Nika Haghtalab , Cameron Musco , Bo Waggoner

Cosine-based softmax losses significantly improve the performance of deep face recognition networks. However, these losses always include sensitive hyper-parameters which can make training process unstable, and it is very tricky to set…

Computer Vision and Pattern Recognition · Computer Science 2019-05-08 Xiao Zhang , Rui Zhao , Junjie Yan , Mengya Gao , Yu Qiao , Xiaogang Wang , Hongsheng Li

We propose a prototype-based approach for improving explainability of softmax classifiers that provides an understandable prediction confidence, generated through stochastic sampling of prototypes, and demonstrates potential for out of…

Machine Learning · Computer Science 2024-07-17 Hilarie Sit , Brendan Keith , Karianne Bergen

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Fusheng Hao , Jun Cheng , Lei Wang , Xinchao Wang , Jianzhong Cao , Xiping Hu , Dapeng Tao

Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can take on much more flexible forms, and should be tailored for…

Computer Vision and Pattern Recognition · Computer Science 2022-05-12 Zhaoqi Leng , Mingxing Tan , Chenxi Liu , Ekin Dogus Cubuk , Xiaojie Shi , Shuyang Cheng , Dragomir Anguelov

Deep Metric Learning (DML) models rely on strong representations and similarity-based measures with specific loss functions. Proxy-based losses have shown great performance compared to pair-based losses in terms of convergence speed.…

Autoencoders are unsupervised deep learning models used for learning representations. In literature, autoencoders have shown to perform well on a variety of tasks spread across multiple domains, thereby establishing widespread…

Computer Vision and Pattern Recognition · Computer Science 2018-10-16 Maneet Singh , Shruti Nagpal , Mayank Vatsa , Richa Singh , Afzel Noore

The classification loss functions used in deep neural network classifiers can be grouped into two categories based on maximizing the margin in either Euclidean or angular spaces. Euclidean distances between sample vectors are used during…

Computer Vision and Pattern Recognition · Computer Science 2022-12-23 Hakan Cevikalp , Hasan Saribas

Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Mei Wang , Weihong Deng , Jiani Hu , Sen Su
‹ Prev 1 4 5 6 7 8 10 Next ›