English
Related papers

Related papers: Are All Losses Created Equal: A Neural Collapse Pe…

200 papers

Supervised-contrastive loss (SCL) is an alternative to cross-entropy (CE) for classification tasks that makes use of similarities in the embedding space to allow for richer representations. In this work, we propose methods to engineer the…

Machine Learning · Computer Science 2023-10-03 Jaidev Gill , Vala Vakilian , Christos Thrampoulidis

Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of requiring correctly annotated large-scale datasets.…

Machine Learning · Computer Science 2018-12-03 Zhilu Zhang , Mert R. Sabuncu

Recent findings reveal that over-parameterized deep neural networks, trained beyond zero training-error, exhibit a distinctive structural pattern at the final layer, termed as Neural-collapse (NC). These results indicate that the final…

Machine Learning · Computer Science 2024-03-01 Tina Behnia , Christos Thrampoulidis

With the ever-increasing complexity of large-scale pre-trained models coupled with a shortage of labeled data for downstream training, transfer learning has become the primary approach in many fields, including natural language processing,…

Machine Learning · Computer Science 2024-07-22 Xiao Li , Sheng Liu , Jinxin Zhou , Xinyu Lu , Carlos Fernandez-Granda , Zhihui Zhu , Qing Qu

Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach \textit{optimal} inter-class separability during the terminal phase of…

Machine Learning · Computer Science 2024-08-15 Enhao Zhang , Chaohua Li , Chuanxing Geng , Songcan Chen

We present the Tamed Cross Entropy (TCE) loss function, a robust derivative of the standard Cross Entropy (CE) loss used in deep learning for classification tasks. However, unlike other robust losses, the TCE loss is designed to exhibit the…

Machine Learning · Computer Science 2018-10-12 Manuel Martinez , Rainer Stiefelhagen

Neural Collapse (NC) gives a precise description of the representations of classes in the final hidden layer of classification neural networks. This description provides insights into how these networks learn features and generalize well…

Machine Learning · Computer Science 2023-08-08 Liam Parker , Emre Onal , Anton Stengel , Jake Intrater

We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has…

Machine Learning · Computer Science 2018-06-07 Quynh Nguyen , Matthias Hein

Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount of experimental evidence has pointed to the propagation of…

Machine Learning · Computer Science 2023-05-23 Peter Súkeník , Marco Mondelli , Christoph Lampert

Neural Collapse (NC) is a well-known phenomenon of deep neural networks in the terminal phase of training (TPT). It is characterized by the collapse of features and classifier into a symmetrical structure, known as simplex equiangular tight…

Machine Learning · Computer Science 2023-10-13 Peifeng Gao , Qianqian Xu , Yibo Yang , Peisong Wen , Huiyang Shao , Zhiyong Yang , Bernard Ghanem , Qingming Huang

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test…

Machine Learning · Statistics 2018-10-31 Timur Garipov , Pavel Izmailov , Dmitrii Podoprikhin , Dmitry Vetrov , Andrew Gordon Wilson

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

In this paper, we propose mean squared error (MSE) loss with outlying label for class imbalanced classification. Cross entropy (CE) loss, which is widely used for image recognition, is learned so that the probability value of true class is…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Sota Kato , Kazuhiro Hotta

Neural Collapse is a phenomenon where the last-layer representations of a well-trained neural network converge to a highly structured geometry. In this paper, we focus on its first (and most basic) property, known as NC1: the within-class…

Machine Learning · Computer Science 2025-02-05 Diyuan Wu , Marco Mondelli

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

In supervised machine learning, the choice of loss function implicitly assumes a particular noise distribution over the data. For example, the frequently used mean squared error (MSE) loss assumes a Gaussian noise distribution. The choice…

Machine Learning · Computer Science 2023-02-15 Thamsanqa Mlotshwa , Heinrich van Deventer , Anna Sergeevna Bosman

For classification, neural networks typically learn by minimizing cross-entropy, but are evaluated and compared using accuracy. This disparity suggests neural loss function search (NLFS), the search for a drop-in replacement loss function…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Brandon Morgan , Dean Hougen

Cross-entropy loss is the standard metric used to train classification models in deep learning and gradient boosting. It is well-known that this loss function fails to account for similarities between the different values of the target. We…

Machine Learning · Statistics 2022-06-16 Brian Lucena

Transferability estimation aims to provide heuristics for quantifying how suitable a pre-trained model is for a specific downstream task, without fine-tuning them all. Prior studies have revealed that well-trained models exhibit the…

Machine Learning · Computer Science 2023-10-10 Yuhe Ding , Bo Jiang , Lijun Sheng , Aihua Zheng , Jian Liang

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