Related papers: UniTSFace: Unified Threshold Integrated Sample-to-…

Face Anti-Spoofing (FAS) is crucial to safeguard Face Recognition (FR) Systems. In real-world scenarios, FRs are confronted with both physical and digital attacks. However, existing algorithms often address only one type of attack at a…

Face Recognition is one of the prominent problems in the computer vision domain. Witnessing advances in deep learning, significant work has been observed in face recognition, which touched upon various parts of the recognition framework…

With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…

Federated learning is a machine learning paradigm in which multiple devices collaboratively train a model under the supervision of a central server while ensuring data privacy. However, its performance is often hindered by redundant,…

Well-annotated medical datasets enable deep neural networks (DNNs) to gain strong power in extracting lesion-related features. Building such large and well-designed medical datasets is costly due to the need for high-level expertise. Model…

One-shot face recognition measures the ability to identify persons with only seeing them at one glance, and is a hallmark of human visual intelligence. It is challenging for conventional machine learning approaches to mimic this way, since…

We reveal critical insights into problems of bias in state-of-the-art facial recognition (FR) systems using a novel Balanced Faces In the Wild (BFW) dataset: data balanced for gender and ethnic groups. We show variations in the optimal…

Non-ideal measurement computed tomography (NICT), which lowers radiation at the cost of image quality, is expanding the clinical use of CT. Although unified models have shown promise in NICT enhancement, most methods require paired data,…

Image classification is hindered by subtle inter-class differences and substantial intra-class variations, which limit the effectiveness of existing contrastive learning methods. Supervised contrastive approaches based on the InfoNCE loss…

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 this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised…

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic…

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes.…

Learning visual representation of high quality is essential for image classification. Recently, a series of contrastive representation learning methods have achieved preeminent success. Particularly, SupCon outperformed the dominant methods…

Federated multi-task learning (FMTL) seeks to collaboratively train customized models for users with different tasks while preserving data privacy. Most existing approaches assume model congruity (i.e., the use of fully or partially…

Face recognition performance has seen a tremendous gain in recent years, mostly due to the availability of large-scale face images dataset that can be exploited by deep neural networks to learn powerful face representations. However, recent…

Ultrasound (US) imaging is clinically invaluable due to its noninvasive and safe nature. However, interpreting US images is challenging, requires significant expertise, and time, and is often prone to errors. Deep learning offers assistive…

In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation,…

We propose a unified representation learning framework to address the Cross Model Compatibility (CMC) problem in the context of visual search applications. Cross compatibility between different embedding models enables the visual search…

Deaths and injuries are common in road accidents, violence, and natural disaster. In such cases, one of the main tasks of responders is to retrieve the identity of the victims to reunite families and ensure proper identification of…