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_0785)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 785 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3125 |
| Val Accuracy | 0.2867 |
| Test Accuracy | 0.2844 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, can, rabbit, willow_tree, skyscraper, mountain, orchid, crab, rose, dolphin, wolf, cattle, clock, palm_tree, tulip, bee, bicycle, spider, pear, squirrel, bowl, rocket, television, elephant, dinosaur, orange, apple, porcupine, cup, bus, shark, fox, lamp, mushroom, girl, possum, chimpanzee, tiger, beaver, snail, plate, lobster, telephone, boy, otter, whale, forest, cloud, camel, raccoon