Related papers: Learning through Creation: A Hash-Free Framework f…

Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed…

Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical organization of real\text{-}world concepts that evolves both…

Generalized Category Discovery (GCD) aims to categorize unlabelled instances from both known and unknown classes by transferring knowledge from labelled data of known classes. Existing methods assume all data comes from a single domain, yet…

Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with applications in robot, protein, and molecule design, among others. A prevalent approach is gradient ascent,…

Class incremental learning (CIL) aims to enable models to continuously learn new classes without catastrophically forgetting old ones. A promising direction is to learn and use prototypes of classes during incremental updates. Despite…

Object-centric learning (OCL) aims to learn representations of individual objects within visual scenes without manual supervision, facilitating efficient and effective visual reasoning. Traditional OCL methods primarily employ bottom-up…

Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data. However, most of the existing works on FL…

In an increasingly digitalized commerce landscape, the proliferation of credit card fraud and the evolution of sophisticated fraudulent techniques have led to substantial financial losses. Automating credit card fraud detection is a viable…

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset, two main categories of methods are used:…

Accurate fault detection in high-dimensional industrial environments remains a major challenge due to the inherent complexity, noise, and redundancy in sensor data. This paper introduces CLAIRE, i.e., a hybrid end-to-end learning framework…

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead…

Out-of-distribution (OOD) detection is crucial for the reliable deployment of machine learning models in real-world scenarios, enabling the identification of unknown samples or objects. A prominent approach to enhance OOD detection…

Semi-supervised learning (SSL) is one of the dominant approaches to address the annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage a large repository of unlabeled data to improve performance while…

The task of Novel Class Discovery (NCD) in semantic segmentation entails training a model able to accurately segment unlabelled (novel) classes, relying on the available supervision from annotated (base) classes. Although extensively…

Although an ever-growing number of applications employ deep learning based systems for prediction, decision-making, or state estimation, almost no certification processes have been established that would allow such systems to be deployed in…

Online Continual Learning (OCL) involves sequentially arriving data and is particularly challenged by catastrophic forgetting, which significantly impairs model performance. To address this issue, we introduce a novel framework, Online…

Object detection is a pivotal task in computer vision that has received significant attention in previous years. Nonetheless, the capability of a detector to localise objects out of the training distribution remains unexplored. Whilst…

The rapid evolution of deepfake generation technologies poses critical challenges for detection systems, as non-continual learning methods demand frequent and expensive retraining. We reframe deepfake detection (DFD) as a Continual Learning…

In many applications of neural network, it is common to introduce huge amounts of input categorical features, as well as output labels. However, since the required network size should have rapid growth with respect to the dimensions of…

Knowledge distillation (KD), best known as an effective method for model compression, aims at transferring the knowledge of a bigger network (teacher) to a much smaller network (student). Conventional KD methods usually employ the teacher…