相关论文: Competing Ratio Loss for Discriminative Multi-clas…

The development of deep convolutional neural network architecture is critical to the improvement of image classification task performance. Many image classification studies use deep convolutional neural network and focus on modifying the…

Building robust and real-time classifiers with diverse datasets are one of the most significant challenges to deep learning researchers. It is because there is a considerable gap between a model built with training (seen) data and real…

In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to…

Convolutional neural networks (CNNs) trained with cross-entropy loss have proven to be extremely successful in classifying images. In recent years, much work has been done to also improve the theoretical understanding of neural networks.…

Modern neural network classifiers achieve remarkable performance across a variety of tasks; however, they frequently exhibit overconfidence in their predictions due to the cross-entropy loss. Inspired by this problem, we propose the…

The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this…

In machine learning, the cost function is crucial because it measures how good or bad a system is. In image classification, well-known networks only consider modifying the network structures and applying cross-entropy loss at the end of the…

Statistical machine learning algorithms have achieved state-of-the-art results on benchmark datasets, outperforming humans in many tasks. However, the out-of-distribution data and confounder, which have an unpredictable causal relationship,…

Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes. To…

Image super-resolution (SR) research has witnessed impressive progress thanks to the advance of convolutional neural networks (CNNs) in recent years. However, most existing SR methods are non-blind and assume that degradation has a single…

Neural networks are trained by minimizing a loss function that defines the discrepancy between the predicted model output and the target value. The selection of the loss function is crucial to achieve task-specific behaviour and highly…

Contrastive Representation Learning (CRL) has achieved strong empirical success in multiple machine learning disciplines, yet its theoretical sample complexity remains poorly understood. Existing analyses usually assume that input tuples…

Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood;…

Residual learning has recently surfaced as an effective means of constructing very deep neural networks for object recognition. However, current incarnations of residual networks do not allow for the modeling and integration of complex…

Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive…

Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets. However, imbalanced class distributions still limit the wide applicability of these models due to…

Curriculum learning can improve neural network training by guiding the optimization to desirable optima. We propose a novel curriculum learning approach for image classification that adapts the loss function by changing the label…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…

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,…