Model-J DINO
Collection
1002 items
โข
Updated
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
๐ Project | ๐ Paper | ๐ป GitHub | ๐ค Dataset
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 329 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9987 |
| Val Accuracy | 0.9165 |
| Test Accuracy | 0.9182 |
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, elephant, pickup_truck, caterpillar, pine_tree, camel, tractor, aquarium_fish, rocket, bee, bowl, skunk, palm_tree, cattle, shrew, boy, forest, sunflower, snail, castle, clock, otter, snake, tulip, man, keyboard, lamp, girl, baby, cockroach, wolf, lobster, turtle, lion, shark, crab, seal, rose, raccoon, crocodile, mouse, pear, cup, wardrobe, bus, dolphin, flatfish, orange, skyscraper, lizard
Base model
facebook/dino-vitb16