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_0702)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 702 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9775 |
| Val Accuracy | 0.8440 |
| Test Accuracy | 0.8394 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, elephant, skyscraper, cattle, cup, cockroach, possum, lamp, beaver, dinosaur, beetle, orchid, road, bridge, woman, lion, seal, keyboard, bottle, porcupine, sweet_pepper, motorcycle, train, willow_tree, flatfish, bus, television, crab, rabbit, apple, chair, trout, hamster, tulip, man, girl, telephone, snake, dolphin, bee, crocodile, maple_tree, sea, raccoon, table, bicycle, wardrobe, bear, shrew, mountain