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_0337)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 337 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9589 |
| Val Accuracy | 0.8717 |
| Test Accuracy | 0.8652 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, chair, lamp, rabbit, fox, trout, forest, boy, shark, otter, turtle, bee, skyscraper, orange, chimpanzee, bus, house, wardrobe, beaver, spider, raccoon, can, plain, elephant, baby, mushroom, beetle, streetcar, dinosaur, lion, bottle, cup, dolphin, girl, ray, snake, apple, road, worm, telephone, porcupine, palm_tree, keyboard, butterfly, caterpillar, tank, mouse, bridge, poppy, hamster