Related papers: Self-Supervised Learning from Images with a Joint-…

Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological learners require. An alternative paradigm has emerged in which…

This work considers the problem of learning structured representations from raw images using self-supervised learning. We propose a principled framework based on a mutual information objective, which integrates self-supervised and structure…

Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject to a bias-variance tradeoff.Without sufficient structural…

This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation used in most masked…

We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containing randomly masked patches to the representation of the…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Joint-Embedding Predictive Architectures (JEPAs), a powerful class of self-supervised models, exhibit an unexplained ability to cluster time-series data by their underlying dynamical regimes. We propose a novel theoretical explanation for…

End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of…

In remote control systems, transmitting large data volumes (e.g., images, video frames) from wireless sensors to remote controllers is challenging when uplink capacity is limited (e.g., RedCap devices or massive wireless sensor networks).…

Recent vision-language-action (VLA) models built upon pretrained vision-language models (VLMs) have achieved significant improvements in robotic manipulation. However, current VLAs still suffer from low sample efficiency and limited…

Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…

In wireless networked control systems, ensuring timely and reliable state updates from distributed devices to remote controllers is essential for robust control performance. However, when multiple devices transmit high-dimensional states…

Acquiring and annotating large datasets in ultrasound imaging is challenging due to low contrast, high noise, and susceptibility to artefacts. This process requires significant time and clinical expertise. Self-supervised learning (SSL)…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

We introduce Brain-JEPA, a brain dynamics foundation model with the Joint-Embedding Predictive Architecture (JEPA). This pioneering model achieves state-of-the-art performance in demographic prediction, disease diagnosis/prognosis, and…

Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can…

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply…

End-to-end autonomous driving increasingly leverages self-supervised video pretraining to learn transferable planning representations. However, pretraining video world models for scene understanding has so far brought only limited…

This paper introduces a two-phase deep feature engineering framework for efficient learning of semantics enhanced joint embedding, which clearly separates the deep feature engineering in data preprocessing from training the text-image joint…