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_0815)
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 | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 815 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2612 |
| Val Accuracy | 0.2435 |
| Test Accuracy | 0.2416 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, rabbit, porcupine, clock, maple_tree, shrew, bowl, orchid, snake, cloud, lawn_mower, wolf, mountain, kangaroo, tractor, television, rose, elephant, mushroom, motorcycle, possum, can, turtle, tiger, sunflower, pickup_truck, tulip, table, leopard, willow_tree, baby, dinosaur, bed, bridge, pear, spider, whale, chair, plate, lobster, butterfly, trout, bee, sweet_pepper, boy, sea, skyscraper, man, beaver, apple