Related papers: One-Shot Domain-Adaptive Imitation Learning via Pr…

Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of…

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…

Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate…

Large pre-trained models are usually fine-tuned on downstream task data, and tested on unseen data. When the train and test data come from different domains, the model is likely to struggle, as it is not adapted to the test domain. We…

Imitation based robot learning has recently gained significant attention in the robotics field due to its theoretical potential for transferability and generalizability. However, it remains notoriously costly, both in terms of hardware and…

Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm,…

Imitation learning with visual observations is notoriously inefficient when addressed with end-to-end behavioural cloning methods. In this paper, we explore an alternative paradigm which decomposes reasoning into three phases. First, a…

Active perception in vision-based robotic manipulation aims to move the camera toward more informative observation viewpoints, thereby providing high-quality perceptual inputs for downstream tasks. Most existing active perception methods…

Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps. Recently, there has been a growing interest in…

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…

As one of the fundamental tasks in computer vision, semantic segmentation plays an important role in real world applications. Although numerous deep learning models have made notable progress on several mainstream datasets with the rapid…

Imitation learning enables robots to learn and replicate human behavior from training data. Recent advances in machine learning enable end-to-end learning approaches that directly process high-dimensional observation data, such as images.…

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…

In this paper, we analyze the behavior of existing techniques and design new solutions for the problem of one-shot visual imitation. In this setting, an agent must solve a novel instance of a novel task given just a single visual…

We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows to learn…

The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques…

Domain adaptation, a pivotal branch of transfer learning, aims to enhance the performance of machine learning models when deployed in target domains with distinct data distributions. This is particularly critical for object detection tasks,…

The automation of robotic tasks requires high precision and adaptability, particularly in force-based operations such as insertions. Traditional learning-based approaches either rely on static datasets, which limit their ability to…

Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer…

Continual learning refers to the ability to acquire and transfer knowledge without catastrophically forgetting what was previously learned. In this work, we consider \emph{few-shot} continual learning in classification tasks, and we propose…