Related papers: Happy: A Debiased Learning Framework for Continual…

Deep clustering as an important branch of unsupervised representation learning focuses on embedding semantically similar samples into the identical feature space. This core demand inspires the exploration of contrastive learning and…

Data imbalance and open-ended distribution are two intrinsic characteristics of the real visual world. Though encouraging progress has been made in tackling each challenge separately, few works dedicated to combining them towards real-world…

Constrained clustering has gained significant attention in the field of machine learning as it can leverage prior information on a growing amount of only partially labeled data. Following recent advances in deep generative models, we…

In this paper, we address Generalized Category Discovery, aiming to simultaneously uncover novel categories and accurately classify known ones. Traditional methods, which lean heavily on self-supervision and contrastive learning, often fall…

Deep learning is typically performed by learning a neural network solely from data in the form of input-output pairs ignoring available domain knowledge. In this work, the Constraint Guided Gradient Descent (CGGD) framework is proposed that…

This work addresses the task of generalized class discovery (GCD) in instance segmentation. The goal is to discover novel classes and obtain a model capable of segmenting instances of both known and novel categories, given labeled and…

Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods…

Current learning algorithms face many difficulties in learning simple patterns and using them to learn more complex ones. They also require more examples than humans do to learn the same pattern, assuming no prior knowledge. In this paper,…

In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labeled set containing different, but related classes. Existing…

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…

Continual Learning (CL) focuses on learning from dynamic and changing data distributions while retaining previously acquired knowledge. Various methods have been developed to address the challenge of catastrophic forgetting, including…

Novel class discovery (NCD) aims to infer novel categories in an unlabeled dataset leveraging prior knowledge of a labeled set comprising disjoint but related classes. Existing research focuses primarily on utilizing the labeled set at the…

The future success of the Navy will depend, in part, on artificial intelligence. In practice, many artificially intelligent algorithms, and in particular deep learning models, rely on continual learning to maintain performance in dynamic…

Generalized Category Discovery (GCD) leverages labeled data to categorize unlabeled samples from known or unknown classes. Most previous methods jointly optimize supervised and unsupervised objectives and achieve promising results. However,…

Unsupervised Continual Learning (UCL) is a burgeoning field in machine learning, focusing on enabling neural networks to sequentially learn tasks without explicit label information. Catastrophic Forgetting (CF), where models forget…

Accurate brain tumor classification is critical for intra-operative decision making in neuro-oncological surgery. However, existing approaches are restricted to a fixed set of predefined classes and are therefore unable to capture patterns…

We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed to first fit the training data with clean labels during an…

On-the-Fly Category Discovery (OCD) aims to recognize known classes while simultaneously discovering emerging novel categories during inference, using supervision only from known classes during offline training. Existing approaches rely…

We tackle the problem of novel class discovery, which aims to learn novel classes without supervision based on labeled data from known classes. A key challenge lies in transferring the knowledge in the known-class data to the learning of…

Deep multi-view clustering methods have achieved remarkable performance. However, all of them failed to consider the difficulty labels (uncertainty of ground-truth for training samples) over multi-view samples, which may result into a…