Related papers: Reachability Embeddings: Scalable Self-Supervised …

In this paper, we explore methods of complicating self-supervised tasks for representation learning. That is, we do severe damage to data and encourage a network to recover them. First, we complicate each of three powerful self-supervised…

In robotic applications, we often face the challenge of discovering new objects while having very little or no labelled training data. In this paper we explore the use of self-supervision provided by a robot traversing an environment to…

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to…

What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions about their internal workings still remain largely…

Fine-grained high-resolution remote sensing mapping typically relies on localized visual features, which restricts cross-domain generalizability and often leads to fragmented predictions of large-scale land covers. While global geospatial…

High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most…

Masked Image Modeling has been one of the most popular self-supervised learning paradigms to learn representations from large-scale, unlabeled Earth Observation images. While incorporating multi-modal and multi-temporal Earth Observation…

Pretraining convolutional neural networks via self-supervision, and applying them in transfer learning, is an incredibly fast-growing field that is rapidly and iteratively improving performance across practically all image domains.…

Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of expensive annotations,…

Human pose estimation is a major computer vision problem with applications ranging from augmented reality and video capture to surveillance and movement tracking. In the medical context, the latter may be an important biomarker for…

Learning meaningful representations is at the heart of many tasks in the field of modern machine learning. Recently, a lot of methods were introduced that allow learning of image representations without supervision. These representations…

Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. However, it is non-trivial to manually design a robot controller that combines modalities with very different characteristics. While…

Self-supervised learning (SSL), which aims to learn meaningful prior representations from unlabeled data, has been proven effective for skeleton-based action understanding. Different from the image domain, skeleton data possesses sparser…

A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or…

Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation learning techniques have not yet become commonplace in the…

In the Vision-and-Language Navigation task, the embodied agent follows linguistic instructions and navigates to a specific goal. It is important in many practical scenarios and has attracted extensive attention from both computer vision and…

Neural implicit representations have become a popular choice for modeling surfaces due to their adaptability in resolution and support for complex topology. While previous works have achieved impressive reconstruction quality by training on…

This work presents a novel domain adaption paradigm for studying contrastive self-supervised representation learning and knowledge transfer using remote sensing satellite data. Major state-of-the-art remote sensing visual domain efforts…

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

We use a contrastive self-supervised learning framework to estimate distances to galaxies from their photometric images. We incorporate data augmentations from computer vision as well as an application-specific augmentation accounting for…