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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 112 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.5253 |
| Val Accuracy | 0.4061 |
| Test Accuracy | 0.4194 |
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, pickup_truck, bear, worm, rabbit, oak_tree, tiger, crocodile, bottle, palm_tree, orange, porcupine, chimpanzee, mountain, lizard, tulip, girl, apple, bridge, skyscraper, clock, cloud, rocket, boy, telephone, snake, mushroom, possum, dinosaur, train, lion, ray, woman, lawn_mower, crab, willow_tree, orchid, mouse, man, elephant, streetcar, lamp, wolf, cup, pine_tree, bowl, beetle, turtle, bus, beaver
Base model
facebook/dino-vitb16