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_0796)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 796 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3420 |
| Val Accuracy | 0.3160 |
| Test Accuracy | 0.3132 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, skyscraper, mountain, lobster, wardrobe, television, crab, worm, girl, mushroom, table, bus, camel, snake, lamp, bed, plate, cup, hamster, skunk, elephant, bear, poppy, mouse, couch, whale, squirrel, spider, cattle, apple, raccoon, orange, sweet_pepper, porcupine, beaver, pear, boy, bridge, kangaroo, man, can, wolf, lion, ray, tiger, sunflower, tulip, motorcycle, leopard, cockroach