Related papers: Transfer learning from synthetic to real images us…

Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide…

Autonomy in robot-assisted minimally invasive surgery has the potential to reduce surgeon cognitive and task load, thereby increasing procedural efficiency. However, implementing accurate autonomous control can be difficult due to poor…

To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the…

Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to…

We present an overview and evaluation of a new, systematic approach for generation of highly realistic, annotated synthetic data for training of deep neural networks in computer vision tasks. The main contribution is a procedural world…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…

Object pose estimation enables robots to understand and interact with their environments. Training with synthetic data is necessary in order to adapt to novel situations. Unfortunately, pose estimation under domain shift, i.e., training on…

Despite great success in human parsing, progress for parsing other deformable articulated objects, like animals, is still limited by the lack of labeled data. In this paper, we use synthetic images and ground truth generated from CAD animal…

In recent years, synthetic data has been widely used in the training of 6D pose estimation networks, in part because it automatically provides perfect annotation at low cost. However, there are still non-trivial domain gaps, such as…

We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…

Well structured visual representations can make robot learning faster and can improve generalization. In this paper, we study how we can acquire effective object-centric representations for robotic manipulation tasks without human labeling…

Sim-to-real transfer is a fundamental challenge in robot reinforcement learning. Discrepancies between simulation and reality can significantly impair policy performance, especially if it receives high-dimensional inputs such as dense depth…

The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We…

The natural world is long-tailed: rare classes are observed orders of magnitudes less frequently than common ones, leading to highly-imbalanced data where rare classes can have only handfuls of examples. Learning from few examples is a…

Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…

Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, which can take…

We aim to detect the class and orientation of a vehicle by training a model with synthetic data. However, the distribution of the classes in the training data is imbalanced, and the model trained on the synthetic image is difficult to…

Robotic ultrasound (US) systems have shown great potential to make US examinations easier and more accurate. Recently, various machine learning techniques have been proposed to realize automatic US image interpretation for robotic US…

Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end…

For driver observation frameworks, clean datasets collected in controlled simulated environments often serve as the initial training ground. Yet, when deployed under real driving conditions, such simulator-trained models quickly face the…