Related papers: Bridging the Gap to Real-World Object-Centric Lear…

Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose a method where general purpose pretrained visual models serve as…

Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled…

With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features…

Unsupervised multi-object segmentation has shown impressive results on images by utilizing powerful semantics learned from self-supervised pretraining. An additional modality such as depth or motion is often used to facilitate the…

World models aim to capture the dynamics of the environment, enabling agents to predict and plan for future states. In most scenarios of interest, the dynamics are highly centered on interactions among objects within the environment. This…

The current state-of-the-art object recognition algorithms, deep convolutional neural networks (DCNNs), are inspired by the architecture of the mammalian visual system, and are capable of human-level performance on many tasks. However, even…

Unsupervised object discovery is becoming an essential line of research for tackling recognition problems that require decomposing an image into entities, such as semantic segmentation and object detection. Recently, object-centric methods…

The advances in unsupervised object-centric representation learning have significantly improved its application to downstream tasks. Recent works highlight that disentangled object representations can aid policy learning in image-based,…

The learning mechanisms by which humans acquire internal representations of objects are not fully understood. Deep neural networks (DNNs) have emerged as a useful tool for investigating this question, as they have internal representations…

We tackle the problem of object-centric learning on point clouds, which is crucial for high-level relational reasoning and scalable machine intelligence. In particular, we introduce a framework, SPAIR3D, to factorize a 3D point cloud into a…

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image…

In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the recursive autoconvolution operator, adopted from physics,…

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…

This paper presents to the best of our knowledge the first end-to-end object tracking approach which directly maps from raw sensor input to object tracks in sensor space without requiring any feature engineering or system identification in…

Object-centric world models (OCWM) aim to decompose visual scenes into object-level representations, providing structured abstractions that could improve compositional generalization and data efficiency in reinforcement learning. We…

Recovering the 3D structure of an object from a single image is a challenging task due to its ill-posed nature. One approach is to utilize the plentiful photos of the same object category to learn a strong 3D shape prior for the object.…

We consider the problem of retrieving objects from image data and learning to classify them into meaningful semantic categories with minimal supervision. To that end, we propose a fully differentiable unsupervised deep clustering approach…

Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual…

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…

We study the challenging problem of unsupervised multi-object segmentation on single images. Existing methods, which rely on image reconstruction objectives to learn objectness or leverage pretrained image features to group similar pixels,…