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 | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 835 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.8973 |
| Test Accuracy | 0.9132 |
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, trout, beetle, butterfly, crab, willow_tree, cloud, bowl, woman, forest, leopard, motorcycle, snail, man, raccoon, plain, rocket, lamp, bus, rabbit, bottle, chimpanzee, apple, poppy, squirrel, whale, couch, lobster, lizard, porcupine, boy, worm, snake, house, pickup_truck, lion, chair, hamster, tank, girl, mouse, dinosaur, crocodile, mountain, mushroom, baby, skyscraper, turtle, orchid, wolf
Base model
facebook/dino-vitb16