相关论文: Avoidance of Manual Labeling in Robotic Autonomous…

Deep Reinforcement Learning has been successfully applied in various computer games [8]. However, it is still rarely used in real-world applications, especially for the navigation and continuous control of real mobile robots [13]. Previous…

As the adoption of deep learning techniques in industrial applications grows with increasing speed and scale, successful deployment of deep learning models often hinges on the availability, volume, and quality of annotated data. In this…

We witnessed a massive growth in the supervised learning paradigm in the past decade. Supervised learning requires a large amount of labeled data to reach state-of-the-art performance. However, labeling the samples requires a lot of human…

Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets. In this paper, we present a label efficient approach and look at jointly learning of multiple dense…

The perception of autonomous vehicles using radars has attracted increased research interest due its ability to operate in fog and bad weather. However, training radar models is hindered by the cost and difficulty of annotating large-scale…

We consider the problem of complementary fashion prediction. Existing approaches focus on learning an embedding space where fashion items from different categories that are visually compatible are closer to each other. However, creating…

Semi-supervised learning provides an effective paradigm for leveraging unlabeled data to improve a model's performance. Among the many strategies proposed, graph-based methods have shown excellent properties, in particular since they allow…

Remote sensing data is crucial for applications ranging from monitoring forest fires and deforestation to tracking urbanization. Most of these tasks require dense pixel-level annotations for the model to parse visual information from…

Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppress the noises in…

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…

Developing a safe and efficient collision avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generate its paths without observing other robots' states and intents. While other distributed…

As the embodiment gap between a robot and a human narrows, new opportunities arise to leverage datasets of humans interacting with their surroundings for robot learning. We propose a novel technique for training sensorimotor policies with…

Data collection in imitation learning often requires significant, laborious human supervision, such as numerous demonstrations, and/or frequent environment resets for methods that incorporate reinforcement learning. In this work, we propose…

We describe a shared control methodology that can, without knowledge of the task, be used to improve a human's control of a dynamic system, be used as a training mechanism, and be used in conjunction with Imitation Learning to generate…

In future 6G cellular networks, a joint communication and sensing protocol will allow the network to perceive the environment, opening the door for many new applications atop a unified communication-perception infrastructure. However,…

Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e.g., television) using only visual observations. A key challenge for current deep reinforcement learning models lies in the…

Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features…

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Reaching the performance of fully supervised learning with unlabeled data and only labeling one sample per class might be ideal for deep learning applications. We demonstrate for the first time the potential for building one-shot…

Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly…