Model-J DINO
Collection
1002 items • Updated
Model-J: DINO Model (model_idx_0646)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 646 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9862 |
| Val Accuracy | 0.8819 |
| Test Accuracy | 0.8694 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, table, chair, bicycle, otter, plate, cup, porcupine, whale, beetle, orange, road, lizard, bottle, cloud, train, bowl, dolphin, pickup_truck, possum, skyscraper, shrew, pear, aquarium_fish, tiger, clock, boy, snake, kangaroo, fox, beaver, orchid, chimpanzee, pine_tree, can, motorcycle, lawn_mower, leopard, oak_tree, lobster, snail, keyboard, forest, crab, sweet_pepper, couch, cattle, flatfish, tank, crocodile
- Downloads last month
- -
Model tree for ProbeX/Model-J__DINO__model_idx_0646
Base model
facebook/dino-vitb16