metadata
base_model: facebook/dino-vitb16
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: DINO Model (model_idx_0778)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 778 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9144 |
| Test Accuracy | 0.9120 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, wardrobe, kangaroo, fox, man, tractor, can, pickup_truck, elephant, bee, porcupine, streetcar, table, rabbit, clock, mountain, shrew, lobster, beetle, crab, motorcycle, oak_tree, rocket, hamster, cockroach, skunk, girl, bridge, mushroom, dinosaur, mouse, pear, otter, palm_tree, bottle, worm, bus, beaver, pine_tree, sunflower, butterfly, seal, chimpanzee, couch, bicycle, woman, ray, crocodile, tulip, lamp