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_0363)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 363 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9791 |
| Val Accuracy | 0.8907 |
| Test Accuracy | 0.8968 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, camel, lobster, mushroom, beetle, tractor, dinosaur, snake, flatfish, elephant, trout, motorcycle, wolf, couch, sea, possum, rabbit, bottle, bridge, seal, chimpanzee, mountain, aquarium_fish, snail, lizard, otter, clock, baby, can, house, leopard, orange, cattle, worm, pickup_truck, telephone, lion, raccoon, road, ray, whale, maple_tree, wardrobe, fox, porcupine, cloud, chair, pine_tree, sweet_pepper, kangaroo