Related papers: SEAL: Self-supervised Embodied Active Learning usi…

Apprenticeship learning has recently attracted a wide attention due to its capability of allowing robots to learn physical tasks directly from demonstrations provided by human experts. Most previous techniques assumed that the state space…

Synthesizing a target concept from a single reference image is challenging in diffusion-based personalized text-to-image generation, particularly for sticker personalization where prompts often require explicit attribute edits. With only…

Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained…

The objective of active learning (AL) is to train classification models with less number of labeled instances by selecting only the most informative instances for labeling. The AL algorithms designed for other data types such as images and…

Embodied artificial intelligence (AI) tasks shift from tasks focusing on internet images to active settings involving embodied agents that perceive and act within 3D environments. In this paper, we investigate the target-driven visual…

Embodied AI has been recently gaining attention as it aims to foster the development of autonomous and intelligent agents. In this paper, we devise a novel embodied setting in which an agent needs to explore a previously unknown environment…

Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performance. In pool-based active learning, accessible unlabeled data…

Self-Supervised Learning (SSL) has emerged as the solution of choice to learn transferable representations from unlabeled data. However, SSL requires to build samples that are known to be semantically akin, i.e. positive views. Requiring…

Semantic segmentation enables robots to perceive and reason about their environments beyond geometry. Most of such systems build upon deep learning approaches. As autonomous robots are commonly deployed in initially unknown environments,…

Verification and validation of autonomous driving (AD) systems and components is of increasing importance, as such technology increases in real-world prevalence. Safety-critical scenario generation is a key approach to robustify AD policies…

Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The quality of annotations tends to deteriorate with the transition…

Robots need robust and flexible vision systems to perceive and reason about their environments beyond geometry. Most of such systems build upon deep learning approaches. As autonomous robots are commonly deployed in initially unknown…

Prior work has primarily formulated CA-HAR as a multi-label classification problem, where model inputs are time-series sensor data and target labels are binary encodings representing whether a given activity or context occurs. These CA-HAR…

Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited…

Obtaining human per-pixel labels for semantic segmentation is incredibly laborious, often making labeled dataset construction prohibitively expensive. Here, we endeavor to overcome this problem with a novel algorithm that combines…

We introduce Perception Learning (PeL), a paradigm that optimizes an agent's sensory interface $f_\phi:\mathcal{X}\to\mathcal{Z}$ using task-agnostic signals, decoupled from downstream decision learning $g_\theta:\mathcal{Z}\to\mathcal{Y}$.…

The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations. However, such annotations are often tedious and expensive to collect. Semi-supervised learning is a good…

This paper addresses the challenge of active perception within autonomous navigation in complex, unknown environments. Revisiting the foundational principles of active perception, we introduce an end-to-end reinforcement learning framework…

We propose a novel robotic system that can improve its perception during deployment. Contrary to the established approach of learning semantics from large datasets and deploying fixed models, we propose a framework in which semantic models…

We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable…