Related papers: Incorporating simulated spatial context informatio…
The deployment of autonomous agents in real-world scenarios is challenged by "unknown unknowns", i.e. novel unexpected environments not encountered during training, such as degraded signs. While existing research focuses on anomaly…
Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…
This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more efficiently than when directly trained on the target…
We train embodied agents to play Visual Hide and Seek where a prey must navigate in a simulated environment in order to avoid capture from a predator. We place a variety of obstacles in the environment for the prey to hide behind, and we…
Wireless localization has become a promising technology for offering intelligent location-based services. Although its localization accuracy is improved under specific scenarios, the short of environmental dynamic vulnerability still…
Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing…
We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness,…
Reinforcement learning is a proven technique for an agent to learn a task. However, when learning a task using reinforcement learning, the agent cannot distinguish the characteristics of the environment from those of the task. This makes it…
Humans rarely perceive objects in isolation but interpret scenes through relationships among co-occurring elements. How such contextual knowledge is acquired without explicit supervision remains unclear. Here we combine human psychophysics…
Contrastive self-supervised learning has attracted significant research attention recently. It learns effective visual representations from unlabeled data by embedding augmented views of the same image close to each other while pushing away…
Embodiment is an important characteristic for all intelligent agents (creatures and robots), while existing scene description tasks mainly focus on analyzing images passively and the semantic understanding of the scenario is separated from…
In recent years supervised representation learning has provided state of the art or close to the state of the art results in semantic analysis tasks including ranking and information retrieval. The core idea is to learn how to embed items…
Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. The ESC performance is heavily dependent on the effectiveness of representative features extracted from the environmental sounds. However,…
A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…
Despite the significant advances in Deep Reinforcement Learning (RL) observed in the last decade, the amount of training experience necessary to learn effective policies remains one of the primary concerns in both simulated and real…
Retrieving accurate semantic information in challenging high dynamic range (HDR) and high-speed conditions remains an open challenge for image-based algorithms due to severe image degradations. Event cameras promise to address these…
We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training. We propose a semi-supervised loss, SuNCEt, based on…
How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question. Traditionally, this has been done with carefully engineered…
Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…
Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…