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_0753)
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 | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 753 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5335 |
| Val Accuracy | 0.4208 |
| Test Accuracy | 0.4062 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
ray, spider, seal, tractor, sea, cattle, television, mouse, turtle, castle, apple, plate, forest, snake, cup, rabbit, plain, leopard, wolf, hamster, crab, oak_tree, willow_tree, baby, dolphin, bowl, pine_tree, possum, shrew, lamp, wardrobe, table, skyscraper, sunflower, maple_tree, pickup_truck, orchid, mountain, bus, lawn_mower, telephone, couch, bottle, palm_tree, tiger, keyboard, can, cloud, road, bridge