Related papers: Learning Object-Centric Video Models by Contrastin…
Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be…
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…
Self-supervision allows learning meaningful representations of natural images, which usually contain one central object. How well does it transfer to multi-entity scenes? We discuss key aspects of learning structured object-centric…
Contrastive learning is commonly applied to self-supervised learning, and has been shown to outperform traditional approaches such as the triplet loss and N-pair loss. However, the requirement of large batch sizes and memory banks has made…
Current state-of-the-art object-centric models use slots and attention-based routing for binding. However, this class of models has several conceptual limitations: the number of slots is hardwired; all slots have equal capacity; training…
Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…
Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…
The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative,…
Unsupervised extraction of objects from low-level visual data is an important goal for further progress in machine learning. Existing approaches for representing objects without labels use structured generative models with static images.…
Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global}…
Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world datasets in restricted…
Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream…
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…
We study three intriguing properties of contrastive learning. First, we generalize the standard contrastive loss to a broader family of losses, and we find that various instantiations of the generalized loss perform similarly under the…
The ability to evolve is fundamental for any valuable autonomous agent whose knowledge cannot remain limited to that injected by the manufacturer. Consider for example a home assistant robot: it should be able to incrementally learn new…
Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches…
Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found…
Developing deep learning models that effectively learn object-centric representations, akin to human cognition, remains a challenging task. Existing approaches facilitate object discovery by representing objects as fixed-size vectors,…
We propose a unified point cloud video self-supervised learning framework for object-centric and scene-centric data. Previous methods commonly conduct representation learning at the clip or frame level and cannot well capture fine-grained…