Downloads · 30 days
0
contrastive-pocket
ARotting/contrastive-pocket
contrastive-pocket is a machine learning model from ARotting. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Contrastive Pocket pretrains a compact vision encoder without labels. Two independently augmented views of every 8x8 digit are pulled together while other examples in the batch act as negatives.
Access
Public
Updated Jul 30, 2026
Parameters
30K
121 KB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors121 KB · 89%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026
- SHA
- 02323ee2
Model card
From the Hugging Face model README
Contrastive Pocket
Contrastive Pocket pretrains a compact vision encoder without labels. Two independently augmented views of every 8x8 digit are pulled together while other examples in the batch act as negatives.
After pretraining, the encoder is frozen. Logistic-regression probes measure held-out classification at 10, 25, and all labeled examples per class. Architecture-matched random encoders and raw-pixel probes provide controls.
Reproduce
uv run python projects/tiny-vision-foundry/prepare_data.py
uv run python projects/contrastive-pocket/train.py
Digit labels are never used in the contrastive optimizer.
Verified results
| Labels per class | Contrastive encoder | Random encoder | Raw pixels |
|---|---|---|---|
| 10 | 89.26% | 79.26% | 90.74% |
| 25 | 92.96% | 82.59% | 93.70% |
| 100 | 96.30% | 81.11% | 97.41% |
The 29,984-parameter encoder substantially outperformed architecture-matched random features at every label budget, while raw pixels remained slightly stronger on this small 8x8 corpus. Its augmented-positive versus mismatched-pair cosine gap was 0.3435, compared with 0.0150 for the random encoder, and its mean embedding standard deviation was 0.1537, providing an explicit non-collapse check.
- License
- apache-2.0
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026