Related papers: Revisiting Mutual Information Maximization for Gen…

We introduce a Parametric Information Maximization (PIM) model for the Generalized Category Discovery (GCD) problem. Specifically, we propose a bi-level optimization formulation, which explores a parameterized family of objective functions,…

In this paper, we tackle the problem of discovering new classes in unlabeled visual data given labeled data from disjoint classes. Existing methods typically first pre-train a model with labeled data, and then identify new classes in…

Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. Previous studies argued that parametric classifiers are prone to overfitting to seen categories,…

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…

Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label information and raise privacy risks. To mitigate this issue, we…

In this paper, a novel pattern classification approach is proposed by regularizing the classifier learning to maximize mutual information between the classification response and the true class label. We argue that, with the learned…

Generalized class discovery (GCD) aims to infer known and unknown categories in an unlabeled dataset leveraging prior knowledge of a labeled set comprising known classes. Existing research implicitly/explicitly assumes that the frequency of…

In this paper, we consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set. Here, the unlabelled images may come from labelled…

In this paper, we tackle the problem of novel visual category discovery, i.e., grouping unlabelled images from new classes into different semantic partitions by leveraging a labelled dataset that contains images from other different but…

Semi-supervised domain generalization (SSDG) has recently emerged as an appealing alternative to tackle domain generalization when labeled data is scarce but unlabeled samples across domains are abundant. In this work, we identify an…

In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to…

While supervised deep learning has achieved great success in a range of applications, relatively little work has studied the discovery of knowledge from unlabeled data. In this paper, we propose an unsupervised deep learning framework to…

Generalized Category Discovery (GCD) aims to identify unlabeled samples by leveraging the base knowledge from labeled ones, where the unlabeled set consists of both base and novel classes. Since clustering methods are time-consuming at…

We propose a novel unsupervised framework for \emph{Invariant Risk Minimization} (IRM), extending the concept of invariance to settings where labels are unavailable. Traditional IRM methods rely on labeled data to learn representations that…

Recent advances in deep learning have significantly improved the performance of various computer vision applications. However, discovering novel categories in an incremental learning scenario remains a challenging problem due to the lack of…

Recent years have witnessed a great success of supervised deep learning, where predictive models were trained from a large amount of fully labeled data. However, in practice, labeling such big data can be very costly and may not even be…

We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance. Most existing semi-supervised methods rely on the assumption that…

Multi-view learning is widely applied to real-life datasets, such as multiple omics biological data, but it often suffers from both missing views and missing labels. Prior probabilistic approaches addressed the missing view problem by using…

We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. This setting is similar to semi-supervised learning, but significantly harder because there are no labelled examples for the…

We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implement many classification problems, including supervised,…