Related papers: Time to augment self-supervised visual representat…

Human is able to conduct 3D recognition by a limited number of haptic contacts between the target object and his/her fingers without seeing the object. This capability is defined as `haptic glance' in cognitive neuroscience. Most of the…

Self-supervised representation learning approaches have recently surpassed their supervised learning counterparts on downstream tasks like object detection and image classification. Somewhat mysteriously the recent gains in performance come…

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…

Data augmentation can be a simple yet powerful tool for autonomous robots to fully utilise available data for selfsupervised identification of atypical scenes or objects. State-of-the-art augmentation methods arbitrarily embed "structural"…

Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have long-tailed label distributions, where we know little…

Populations of neurons in inferotemporal cortex (IT) maintain an explicit code for object identity that also tolerates transformations of object appearance e.g., position, scale, viewing angle [1, 2, 3]. Though the learning rules are not…

Self-supervised learning (SSL) has emerged as a powerful framework to learn representations from raw data without supervision. Yet in practice, engineers face issues such as instability in tuning optimizers and collapse of representations…

Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…

Self-supervision has shown outstanding results for natural language processing, and more recently, for image recognition. Simultaneously, vision transformers and its variants have emerged as a promising and scalable alternative to…

Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain specific knowledge. This challenge is magnified in natural language processing where no general rules exist for…

Self-supervised learning (SSL) has the potential to benefit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, existing…

In this paper, we present an approach for learning a visual representation from the raw spatiotemporal signals in videos. Our representation is learned without supervision from semantic labels. We formulate our method as an unsupervised…

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…

We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local…

Offline reinforcement learning proposes to learn policies from large collected datasets without interacting with the physical environment. These algorithms have made it possible to learn useful skills from data that can then be deployed in…

Some of the threats in the dynamic environment include the unpredictability of the motion of objects and interferences to the robotic grasp. In such conditions the traditional supervised and reinforcement learning approaches are ill suited…

Self-supervised learning (SSL) is a growing torrent that has recently transformed machine learning and its many real world applications, by learning on massive amounts of unlabeled data via self-generated supervisory signals. Unsupervised…

We propose a self-supervised approach for learning representations of objects from monocular videos and demonstrate it is particularly useful in situated settings such as robotics. The main contributions of this paper are: 1) a…