Related papers: Dynamic Class Queue for Large Scale Face Recogniti…

Federated Learning enables visual models to be trained on-device, bringing advantages for user privacy (data need never leave the device), but challenges in terms of data diversity and quality. Whilst typical models in the datacenter are…

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the…

In this work, we address the challenging task of long-tailed image recognition. Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail…

Deep learning has received increasing interests in face recognition recently. Large quantities of deep learning methods have been proposed to handle various problems appeared in face recognition. Quite a lot deep methods claimed that they…

Facial recognition has become a widely used method for authentication and identification, with applications for secure access and locating missing persons. Its success is largely attributed to deep learning, which leverages large datasets…

Deep Neural Networks (DNNs) have established themselves as a dominant technique in machine learning. DNNs have been top performers on a wide variety of tasks including image classification, speech recognition, and face recognition.…

Real-world large-scale datasets are both noisily labeled and class-imbalanced. The issues seriously hurt the generalization of trained models. It is hence significant to address the simultaneous incorrect labeling and class-imbalance, i.e.,…

Imbalanced classification datasets pose significant challenges in machine learning, often leading to biased models that perform poorly on underrepresented classes. With the rise of foundation models, recent research has focused on the full,…

We consider a multi-class queueing model of a telephone call center, in which a system manager dynamically allocates available servers to customer calls. Calls can terminate through either service completion or customer abandonment, and the…

Deep neural networks perform poorly on heavily class-imbalanced datasets. Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognition. Based on the…

Facial Expression Recognition faces two core challenges. The first is class imbalance in public datasets, which skews the learning process and weakens generalization. The second is related to privacy and data collection constraints, which…

We study a classification problem where each feature can be acquired for a cost and the goal is to optimize a trade-off between the expected classification error and the feature cost. We revisit a former approach that has framed the problem…

Large facial variations are the main challenge in face recognition. To this end, previous variation-specific methods make full use of task-related prior to design special network losses, which are typically not general among different tasks…

Many advances of deep learning techniques originate from the efforts of addressing the image classification task on large-scale datasets. However, the construction of such clean datasets is costly and time-consuming since the Internet is…

A novel procedure is presented in this paper, for training a deep convolutional and recurrent neural network, taking into account both the available training data set and some information extracted from similar networks trained with other…

Image segmentation based on continual learning exhibits a critical drop of performance, mainly due to catastrophic forgetting and background shift, as they are required to incorporate new classes continually. In this paper, we propose a…

Face recognition has long been an active research area in the field of artificial intelligence, particularly since the rise of deep learning in recent years. In some practical situations, each identity has only a single sample available for…

Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active…

Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions. To…

Modern machine learning suffers from catastrophic forgetting when learning new classes incrementally. The performance dramatically degrades due to the missing data of old classes. Incremental learning methods have been proposed to retain…