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_0944)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 944 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9620 |
| Val Accuracy | 0.8429 |
| Test Accuracy | 0.8346 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, willow_tree, whale, rocket, apple, rabbit, cockroach, sunflower, girl, pickup_truck, boy, couch, lobster, wolf, telephone, plain, orchid, tank, bicycle, snake, wardrobe, lion, rose, beaver, skunk, flatfish, crab, table, man, shark, caterpillar, cloud, porcupine, mushroom, bridge, fox, castle, elephant, forest, can, woman, skyscraper, trout, motorcycle, bear, maple_tree, clock, shrew, chimpanzee, squirrel