English
Related papers

Related papers: On the Implicit Geometry of Cross-Entropy Paramete…

200 papers

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

Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure…

Machine Learning · Computer Science 2022-10-19 Damien Dablain , Colin Bellinger , Bartosz Krawczyk , Nitesh Chawla

Most segmentation losses are arguably variants of the Cross-Entropy (CE) or Dice losses. On the surface, these two categories of losses seem unrelated, and there is no clear consensus as to which category is a better choice, with varying…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Bingyuan Liu , Jose Dolz , Adrian Galdran , Riadh Kobbi , Ismail Ben Ayed

Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of…

Machine Learning · Computer Science 2018-12-05 Elad Hoffer , Nir Ailon

From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of encoding biases that…

Machine Learning · Computer Science 2021-09-07 Ferran Alet , Maria Bauza , Kenji Kawaguchi , Nurullah Giray Kuru , Tomas Lozano-Perez , Leslie Pack Kaelbling

Convolutional neural networks (CNNs) have achieved impressive results on imbalanced image data, but they still have difficulty generalizing to minority classes and their decisions are difficult to interpret. These problems are related…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Damien Dablain , Kristen N. Jacobson , Colin Bellinger , Mark Roberts , Nitesh Chawla

The objective in extreme multi-label learning is to train a classifier that can automatically tag a novel data point with the most relevant subset of labels from an extremely large label set. Embedding based approaches make training and…

Machine Learning · Computer Science 2015-07-13 Kush Bhatia , Himanshu Jain , Purushottam Kar , Prateek Jain , Manik Varma

In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks. Cross Entropy (CE) loss has been shown to be not robust to noisy labels due to its…

Machine Learning · Computer Science 2023-06-14 Hongxin Wei , Huiping Zhuang , Renchunzi Xie , Lei Feng , Gang Niu , Bo An , Yixuan Li

Class imbalance poses a challenge for developing unbiased, accurate predictive models. In particular, in image segmentation neural networks may overfit to the foreground samples from small structures, which are often heavily…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Zeju Li , Konstantinos Kamnitsas , Ben Glocker

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how…

Machine Learning · Computer Science 2026-03-25 Shengping Xie , Zekun Wu , Quan Chen , Kaixu Tang

Large-scale network embedding is to learn a latent representation for each node in an unsupervised manner, which captures inherent properties and structural information of the underlying graph. In this field, many popular approaches are…

Machine Learning · Computer Science 2020-12-11 Shengzhong Zhang , Zengfeng Huang , Haicang Zhou , Ziang Zhou

For challenging machine learning problems such as zero-shot learning and fine-grained categorization, embedding learning is the machinery of choice because of its ability to learn generic notions of similarity, as opposed to class-specific…

Computer Vision and Pattern Recognition · Computer Science 2019-12-19 Ujjal Kr Dutta , Mehrtash Harandi , Chandra Sekhar Chellu

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly developed for a single…

Social and Information Networks · Computer Science 2021-05-06 Xiao Shen , Quanyu Dai , Sitong Mao , Fu-lai Chung , Kup-Sze Choi

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in…

Machine Learning · Computer Science 2019-10-29 Kaidi Cao , Colin Wei , Adrien Gaidon , Nikos Arechiga , Tengyu Ma

Due to the inherent imbalance in real-world datasets, na\"ive Empirical Risk Minimization (ERM) tends to bias the learning process towards the majority classes, hindering generalization to minority classes. To rebalance the learning…

Machine Learning · Computer Science 2025-12-09 Zitai Wang , Qianqian Xu , Zhiyong Yang , Zhikang Xu , Linchao Zhang , Xiaochun Cao , Qingming Huang

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

Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness,…

Machine Learning · Computer Science 2018-11-20 Dallas Card , Michael Zhang , Noah A. Smith

Cross-entropy (CE) loss is the de-facto standard for training deep neural networks to perform classification. However, CE-trained deep neural networks struggle with robustness and generalisation issues. To alleviate these issues, we propose…

Machine Learning · Computer Science 2025-01-22 Michael W. Spratling , Heiko H. Schütt

This paper presents a novel method for embedding transfer, a task of transferring knowledge of a learned embedding model to another. Our method exploits pairwise similarities between samples in the source embedding space as the knowledge,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Sungyeon Kim , Dongwon Kim , Minsu Cho , Suha Kwak