Related papers: Softmax Dissection: Towards Understanding Intra- a…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domains, or by introducing unlabeled target variation data to…

The goal of this work is to train discriminative cross-modal embeddings without access to manually annotated data. Recent advances in self-supervised learning have shown that effective representations can be learnt from natural cross-modal…

Face recognition is one of the most widely publicized feature in the devices today and hence represents an important problem that should be studied with the utmost priority. As per the recent trends, the Convolutional Neural Network (CNN)…

In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. A typical pipeline for face verification includes training a deep network for…

Softmax is a standard final layer used in Neural Nets (NNs) to summarize information encoded in the trained NN and return a prediction. However, Softmax leverages only a subset of the class-specific structure encoded in the trained model…

The cross-entropy softmax loss is the primary loss function used to train deep neural networks. On the other hand, the focal loss function has been demonstrated to provide improved performance when there is an imbalance in the number of…

Deep Learning has revolutionized machine learning and artificial intelligence, achieving superhuman performance in several standard benchmarks. It is well-known that deep learning models are inefficient to train; they learn by processing…

Enabling machine learning classifiers to defer their decision to a downstream expert when the expert is more accurate will ensure improved safety and performance. This objective can be achieved with the learning-to-defer framework which…

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…

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for…

Deep neural networks enable real-time monitoring of in-vehicle drivers, facilitating the timely prediction of distractions, fatigue, and potential hazards. This technology is now integral to intelligent transportation systems. Recent…

In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending. In specific, in the training…

Large language models (LLMs) have brought significant and transformative changes in human society. These models have demonstrated remarkable capabilities in natural language understanding and generation, leading to various advancements and…

Following the rapidly growing digital image usage, automatic image categorization has become preeminent research area. It has broaden and adopted many algorithms from time to time, whereby multi-feature (generally, hand-engineered features)…

In recent years, the multimedia forensics and security community has seen remarkable progress in multitask learning for DeepFake (i.e., face forgery) detection. The prevailing approach has been to frame DeepFake detection as a binary…

In replay-based methods for continual learning, replaying input samples in episodic memory has shown its effectiveness in alleviating catastrophic forgetting. However, the potential key factor of cross-entropy loss with softmax in causing…

This paper investigates the learning theory of Transformer networks for regression tasks on the compact Euclidean domain $[0,1]^d$ and $d$-dimensional compact Riemannian manifolds. We propose a novel constructive approximation framework for…

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…

The automatic diagnosis of various retinal diseases from fundus images is important to support clinical decision-making. However, developing such automatic solutions is challenging due to the requirement of a large amount of human-annotated…