Related papers: Exploring the Open World Using Incremental Extreme…

In a constantly changing world, animals must account for environmental volatility when making decisions. To appropriately discount older, irrelevant information, they need to learn the rate at which the environment changes. We develop an…

Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing,…

Interacting with the actual environment to acquire data is often costly and time-consuming in robotic tasks. Model-based offline reinforcement learning (RL) provides a feasible solution. On the one hand, it eliminates the requirements of…

Numerous offline and model-based reinforcement learning systems incorporate world models to emulate the inherent environments. A world model is particularly important in scenarios where direct interactions with the real environment is…

Training deep reinforcement learning agents on environments with multiple levels / scenes / conditions from the same task, has become essential for many applications aiming to achieve generalization and domain transfer from simulation to…

Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing visual perception challenges, such as localizing certain…

The interest in Artificial Intelligence (AI) and its applications has seen unprecedented growth in the last few years. The success can be partly attributed to the advancements of deep neural networks made in the sub-fields of AI such as…

Open World Object Detection(OWOD) addresses realistic scenarios where unseen object classes emerge, enabling detectors trained on known classes to detect unknown objects and incrementally incorporate the knowledge they provide. While…

Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., ViT) are following the same trend, achieving the best…

We consider the generic problem of detecting low-level structures in images, which includes segmenting the manipulated parts, identifying out-of-focus pixels, separating shadow regions, and detecting concealed objects. Whereas each such…

Empirical risk minimization can lead to poor generalization behavior on unseen environments if the learned model does not capture invariant feature representations. Invariant risk minimization (IRM) is a recent proposal for discovering…

Recognising relevant objects or object states in its environment is a basic capability for an autonomous robot. The dominant approach to object recognition in images and range images is classification by supervised machine learning,…

Real-world object detection must operate in evolving environments where new classes emerge, domains shift, and unseen objects must be identified as "unknown": all without accessing prior data. We introduce Evolving World Object Detection…

In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world applications where inference latency is a concern. To tackle…

Recently, learning discriminative features to improve the recognition performances gradually becomes the primary goal of deep learning, and numerous remarkable works have emerged. In this paper, we propose a novel yet extremely simple…

Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into…

As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents continuously learn new…

High-dimensional data is common in multiple areas, such as health care and genomics, where the number of features can be tens of thousands. In such scenarios, the large number of features often leads to inefficient learning. Constraint…

We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image…

Neural rendering algorithms introduce a fundamentally new approach for photorealistic rendering, typically by learning a neural representation of illumination on large numbers of ground truth images. When training for a given variable…