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_0946)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 946 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9520 |
| Val Accuracy | 0.8445 |
| Test Accuracy | 0.8466 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, lizard, bridge, raccoon, beetle, mountain, aquarium_fish, mushroom, bottle, leopard, tiger, camel, chair, butterfly, baby, caterpillar, motorcycle, telephone, rocket, lobster, crab, worm, streetcar, fox, possum, lamp, bed, tractor, television, rose, trout, wolf, whale, snail, beaver, cattle, man, cockroach, castle, boy, lion, can, kangaroo, dinosaur, dolphin, apple, shrew, bus, pine_tree, porcupine