In computer vision, it is often observed that formulating regression problems as a
classification task often yields better performance. We investigate this curious phenomenon …

Two things seem to be indisputable in the contemporary deep learning discourse: 1. The
categorical cross-entropy loss after softmax activation is the method of choice for …

Deep neural networks have achieved remarkable performance on a range of classification
tasks, with softmax cross-entropy (CE) loss emerging as the de-facto objective function. The …

Assisted by the availability of data and high performance computing, deep learning
techniques have achieved breakthroughs and surpassed human performance empirically in …

Abstract 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 …

Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are
ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class …

Deep regression models typically learn in an end-to-end fashion without explicitly
emphasizing a regression-aware representation. Consequently, the learned representations …

Cross-entropy loss together with softmax is arguably one of the most common used
supervision components in convolutional neural networks (CNNs). Despite its simplicity …

Deep-learning architectures for classification problems involve the cross-entropy loss
sometimes assisted with auxiliary loss functions like center loss, contrastive loss and triplet …

While deep neural networks are highly effective at solving complex tasks, large pre-trained
models are commonly employed even to solve consistently simpler downstream tasks …