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_0370)
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 | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 370 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.8960 |
| Test Accuracy | 0.9008 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, bridge, palm_tree, worm, lobster, sea, road, rabbit, bottle, rose, keyboard, train, bicycle, television, turtle, cattle, dolphin, girl, tank, kangaroo, cloud, crocodile, cup, flatfish, otter, boy, mushroom, plain, possum, ray, camel, motorcycle, skyscraper, mountain, shrew, shark, snail, chimpanzee, trout, baby, man, couch, lawn_mower, raccoon, squirrel, pear, beaver, mouse, crab, whale