Pocket JEPA

Pocket JEPA is a small-compute joint-embedding predictive architecture for 8x8 visual worlds. The online network sees a partially hidden image and predicts the latent representation produced by an exponential-moving-average target encoder on the complete image. It never reconstructs pixels and never uses class labels during pretraining.

The experiment measures whether the learned J-space becomes useful under a strict ten-labels-per-class linear-probe budget. An architecture-matched random encoder and a raw-pixel probe are retained as controls. A separate masked-view evaluation tests whether predictive pretraining creates occlusion-tolerant features.

This is a compact JEPA-inspired experiment, not an implementation or reproduction claim for any specific large-scale I-JEPA result.

Verified results

After 260 unlabeled pretraining epochs on 1,347 images, a linear classifier received only ten labels per class:

Representation Clean accuracy Unseen block-mask accuracy
Pocket JEPA 89.56% 85.78%
Architecture-matched random encoder 74.44% 55.56%
Raw pixels 88.67% 72.22%

The deployed encoder has 14,848 parameters. Its training-only predictor has 4,192 parameters. Pocket JEPA improved the masked-view result by 30.22 points over the random encoder and 13.56 points over raw pixels.

Reproduce

uv run python projects/pocket-jepa/train.py
Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
14.8k params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support