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_0355)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 355 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5041 |
| Val Accuracy | 0.4136 |
| Test Accuracy | 0.4232 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, kangaroo, keyboard, worm, cloud, can, pickup_truck, bus, elephant, girl, mouse, palm_tree, pine_tree, lobster, telephone, flatfish, plate, seal, table, chimpanzee, pear, maple_tree, couch, possum, mushroom, beaver, lawn_mower, crab, bridge, shrew, hamster, motorcycle, baby, television, orange, bottle, tulip, house, leopard, streetcar, orchid, trout, bicycle, wardrobe, aquarium_fish, train, tractor, otter, cockroach, turtle