Related papers: Learning to Discover: A Generalized Framework for …

Continual Generalized Category Discovery (C-GCD) faces a critical challenge: incrementally learning new classes from unlabeled data streams while preserving knowledge of old classes. Existing methods struggle with catastrophic forgetting,…

Constantly discovering novel concepts is crucial in evolving environments. This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD), which aims to incrementally discover new classes from unlabeled data…

In open-world scenarios, Generalized Category Discovery (GCD) requires identifying both known and novel categories within unlabeled data. However, existing methods often suffer from prototype confusion caused by shortcut learning, which…

Previous research contributions on blind lossy compression identification report near perfect performance metrics on their test set, across a variety of codecs and bit rates. However, we show that such results can be deceptive and may not…

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of…

Multimodal movie genre classification has always been regarded as a demanding multi-label classification task due to the diversity of multimodal data such as posters, plot summaries, trailers and metadata. Although existing works have made…

Music Structure Analysis (MSA) aims to uncover the high-level organization of musical pieces. State-of-the-art methods are often based on supervised deep learning, but these methods are bottlenecked by the need for heavily annotated data…

Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models,…

One important desideratum of lifelong learning aims to discover novel classes from unlabelled data in a continuous manner. The central challenge is twofold: discovering and learning novel classes while mitigating the issue of catastrophic…

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…

The identification and quantification of markers in medical images is critical for diagnosis, prognosis and management of patients in clinical practice. Supervised- or weakly supervised training enables the detection of findings that are…

The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks, this needs gathering training data that covers a number of…

Federated learning aims to share private data to maximize the data utility without privacy leakage. Previous federated learning research mainly focuses on multi-class classification problems. However, multi-label classification is a crucial…

In clinical practice, automatic analysis of electrocardiogram (ECG) is widely applied to identify irregular heart rhythms and other electrical anomalies of the heart, enabling timely intervention and potentially improving clinical outcomes.…

Causal representation learning (CRL) offers the promise of uncovering the underlying causal model by which observed data was generated, but the practical applicability of existing methods remains limited by the strong assumptions required…

Retrieval-Augmented Generation (RAG), by incorporating external knowledge with parametric memory of language models, has become the state-of-the-art architecture for open-domain QA tasks. However, common knowledge bases are inherently…

Music genres allow to categorize musical items that share common characteristics. Although these categories are not mutually exclusive, most related research is traditionally focused on classifying tracks into a single class. Furthermore,…

Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose…

There have been significant advancements in anomaly detection in an unsupervised manner, where only normal images are available for training. Several recent methods aim to detect anomalies based on a memory, comparing or reconstructing the…

Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information…