相关论文: Proxy-Anchor and EVT-Driven Continual Learning Met…

As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…

If an unknown example that is not seen during training appears, most recognition systems usually produce overgeneralized results and determine that the example belongs to one of the known classes. To address this problem,…

Conventional extreme learning machines solve a Moore-Penrose generalized inverse of hidden layer activated matrix and analytically determine the output weights to achieve generalized performance, by assuming the same loss from different…

Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel…

Extreme value theory (EVT) is a statistical tool for analysis of extreme events. It has a strong theoretical background, however, we need to choose hyper-parameters to apply EVT. In recent studies of machine learning, techniques of choosing…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Generalized Category Discovery (GCD) aims to classify unlabeled data containing both seen and novel categories. Although existing methods perform well on generic datasets, they struggle in fine-grained scenarios. We attribute this…

Continual learning for Semantic Segmentation (CSS) is a rapidly emerging field, in which the capabilities of the segmentation model are incrementally improved by learning new classes or new domains. A central challenge in Continual Learning…

Incremental class learning, a scenario in continual learning context where classes and their training data are sequentially and disjointedly observed, challenges a problem widely known as catastrophic forgetting. In this work, we propose a…

Most of the existing classification methods are aimed at minimization of empirical risk (through some simple point-based error measured with loss function) with added regularization. We propose to approach this problem in a more information…

Deep neural networks have achieved state-of-the-art performance in a wide range of recognition/classification tasks. However, when applying deep learning to real-world applications, there are still multiple challenges. A typical challenge…

Current works in human emotion recognition follow the traditional closed learning approach governed by rigid rules without any consideration of novelty. Classification models are trained on some collected datasets and expected to have the…

Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes. Given that knowledge learned…

Representations learned by self-supervised approaches are generally considered to possess sufficient generalizability and discriminability. However, we disclose a nontrivial mutual-exclusion relationship between these critical…

Class incremental learning consists in training discriminative models to classify an increasing number of classes over time. However, doing so using only the newly added class data leads to the known problem of catastrophic forgetting of…

Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.e., adapting the original model trained on a set of classes to additionally detect objects of new classes, in the absence…

Deep Metric Learning (DML) models rely on strong representations and similarity-based measures with specific loss functions. Proxy-based losses have shown great performance compared to pair-based losses in terms of convergence speed.…

Large-scale vision-language models (VLMs) have shown a strong zero-shot generalization capability on unseen-domain data. However, adapting pre-trained VLMs to a sequence of downstream tasks often leads to the forgetting of previously…

Uncertainty quantification of deep neural networks has become an active field of research and plays a crucial role in various downstream tasks such as active learning. Recent advances in evidential deep learning shed light on the direct…

Continual Learning (CL) seeks to build an agent that can continuously learn a sequence of tasks, where a key challenge, namely Catastrophic Forgetting, persists due to the potential knowledge interference among different tasks. On the other…