REVIEW 4 cited by
MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Self-supervised learning of visual representations has been focusing on learning content features, which do not capture object motion or location, and focus on identifying and differentiating objects in images and videos. On the other hand, optical flow estimation is a task that does not involve understanding the content of the images on which it is estimated. We unify the two approaches and introduce MC-JEPA, a joint-embedding predictive architecture and self-supervised learning approach to jointly learn optical flow and content features within a shared encoder, demonstrating that the two associated objectives; the optical flow estimation objective and the self-supervised learning objective; benefit from each other and thus learn content features that incorporate motion information. The proposed approach achieves performance on-par with existing unsupervised optical flow benchmarks, as well as with common self-supervised learning approaches on downstream tasks such as semantic segmentation of images and videos.
Forward citations
Cited by 4 Pith papers
-
A New Perspective On AI Safety Through Control Theory Methodologies
This paper outlines a new conceptual paradigm, data control, which transfers control-theoretic system analysis and properties to AI systems to support generic AI safety assurance.
-
Discrete JEPA: Learning Discrete Token Representations without Reconstruction
Discrete-JEPA learns discrete semantic image tokens through latent predictive coding without pixel reconstruction, and achieves stable long-horizon prediction on synthetic symbolic tasks.
-
Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions
CHARM is a 7M-parameter self-supervised embedding model for multivariate time series that uses channel descriptions to beat specialized baselines on forecasting, classification, and anomaly detection.
-
Optimisation Is Not What You Need
A formal-style claim that loss-minimizing weighted learners cannot avoid catastrophic forgetting or overfitting, with a limited demonstration on the author's own world-modelling algorithm.
Discussion (0). Continue with ORCID to comment.