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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 62 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9960 |
| Val Accuracy | 0.9115 |
| Test Accuracy | 0.9022 |
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, can, bowl, mouse, rose, clock, baby, dolphin, turtle, leopard, worm, pear, lion, elephant, boy, hamster, rabbit, castle, tractor, shrew, fox, plain, crocodile, possum, forest, mushroom, pickup_truck, dinosaur, snail, beaver, woman, lamp, raccoon, sunflower, motorcycle, pine_tree, man, rocket, squirrel, snake, bicycle, oak_tree, cockroach, chimpanzee, bottle, crab, aquarium_fish, wolf, bus, skyscraper
Base model
facebook/dino-vitb16