Related papers: No Representation Rules Them All in Category Disco…

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…

Despite their effectiveness, current deep learning models face challenges with images coming from different domains with varying appearance and content. We introduce SegCLR, a versatile framework designed to segment images across different…

Federated Graph Learning (FGL) enables collaborative learning over distributed graph data, yet existing approaches largely rely on a closed-world assumption, limiting their applicability in dynamic environments where novel categories…

Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of…

Combining clustering and representation learning is one of the most promising approaches for unsupervised learning of deep neural networks. However, doing so naively leads to ill posed learning problems with degenerate solutions. In this…

Category discovery methods aim to find novel categories in unlabeled visual data. At training time, a set of labeled and unlabeled images are provided, where the labels correspond to the categories present in the images. The labeled data…

Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to prevent forgetting the old…

Neural network-based clustering has recently gained popularity, and in particular a constrained clustering formulation has been proposed to perform transfer learning and image category discovery using deep learning. The core idea is to…

Novel Class Discovery (NCD) involves identifying new categories within unlabeled data by utilizing knowledge acquired from previously established categories. However, existing NCD methods often struggle to maintain a balance between the…

Graph contrastive learning (GCL) has been widely applied to text classification tasks due to its ability to generate self-supervised signals from unlabeled data, thus facilitating model training. However, existing GCL-based text…

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…

We introduce the first unified framework for *Fine-Grained Domain-Generalized Generalized Category Discovery* (FG-DG-GCD), bringing open-world recognition closer to real-world deployment under domain shift. Unlike conventional GCD, which…

A ubiquitous challenge in machine learning is the problem of domain generalisation. This can exacerbate bias against groups or labels that are underrepresented in the datasets used for model development. Model bias can lead to unintended…

Clustering is a fundamental machine learning task which has been widely studied in the literature. Classic clustering methods follow the assumption that data are represented as features in a vectorized form through various representation…

Unsupervised clustering on speakers is becoming increasingly important for its potential uses in semi-supervised learning. In reality, we are often presented with enormous amounts of unlabeled data from multi-party meetings and discussions.…

This work generalizes the problem of unsupervised domain generalization to the case in which no labeled samples are available (completely unsupervised). We are given unlabeled samples from multiple source domains, and we aim to learn a…

In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It could easily be the…

Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models, creating a potential of learning from large-scale…

Generalising deep networks to novel domains without manual labels is challenging to deep learning. This problem is intrinsically difficult due to unpredictable changing nature of imagery data distributions in novel domains. Pre-learned…

Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets, and is critical for understanding model behaviors in various unseen environments. In the absence of image labels, based on dataset representations,…