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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 841 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.3306 |
| Val Accuracy | 0.3024 |
| Test Accuracy | 0.2914 |
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, bed, hamster, ray, aquarium_fish, clock, chair, shrew, rabbit, tiger, flatfish, spider, turtle, cattle, baby, motorcycle, mouse, poppy, lobster, dinosaur, lamp, otter, plain, raccoon, maple_tree, plate, worm, mountain, keyboard, cloud, possum, lion, butterfly, pear, lizard, kangaroo, pine_tree, snake, tulip, skyscraper, porcupine, bus, beetle, can, mushroom, willow_tree, pickup_truck, bear, dolphin, snail
Base model
facebook/dino-vitb16