paper-with-me

홈 › Papers

Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning

2024-10-14 · Etai Littwin, Vimal Thilak, Anand Gopalakrishnan

Image-based Joint-Embedding Predictive Architecture (IJEPA) offers an attractive alternative to Masked Autoencoder (MAE) for representation learning using the Masked Image Modeling framework. IJEPA drives representations to capture useful semantic information by predicting in latent rather than input space. However, IJEPA relies on carefully designed context and target windows to avoid representational collapse. The encoder modules in IJEPA cannot adaptively modulate the type of predicted and/or target features based on the feasibility of the masked prediction task as they are not given sufficient information of both context and targets. Based on the intuition that in natural images, information has a strong spatial bias with spatially local regions being highly predictive of one another compared to distant ones. We condition the target encoder and context encoder modules in IJEPA with positions of context and target windows respectively. Our "conditional" encoders show performance gains on several image classification benchmark datasets, improved robustness to context window size and sample-efficiency during pretraining.

📄 PDF Abstract BibTeX arXiv:2410.10773

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationRepresentation Learning

Similar Papers 제목 키워드 기반

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density

2025-10-07 · Randall Balestriero, Nicolas Ballas, Mike Rabbat, Yann LeCun arxiv

Joint Embedding Predictive Architectures (JEPAs) learn representations able to solve numerous downstream tasks out-of-the-box. JEPAs combine two objectives: (i) a latent-space prediction term, i.e., the representation of…

Density EstimationOutlier Detection

Pretext Matters: An Empirical Study of SSL Methods in Medical Imaging

2026-03-23 · Vedrana Ivezić, Mara Pleasure, Ashwath Radhachandran, Saarang Panchavati 외 arxiv

Though self-supervised learning (SSL) has demonstrated incredible ability to learn robust representations from unlabeled data, the choice of optimal SSL strategy can lead to vastly different performance outcomes in speci…

Self-Supervised Learning

KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning

2025-12-22 · Eric Zimmermann, Harley Wiltzer, Justin Szeto, David Alvarez-Melis 외 arxiv

Recent breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations toward isotropic Gaussian priors yields provable gains in training sta…

Self-Supervised Learning

S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention

2024-03-18 · Pierre Guetschel, Thomas Moreau, Michael Tangermann

Motivated by the challenge of seamless cross-dataset transfer in EEG signal processing, this article presents an exploratory study on the use of Joint Embedding Predictive Architectures (JEPAs). In recent years, self-sup…

Brain Computer InterfaceBrain DecodingEEGERP+4

Orthogonal JEPA: Factorized Predictive States for Latent World Models

2026-08-20 · Taoyong Cui, Pheng Ann Heng, Wanli Ouyang arxiv

World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a direct way to learn such states by predicting tar…

Continuous Control