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 | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 312 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9653 |
| Val Accuracy | 0.8685 |
| Test Accuracy | 0.8698 |
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, squirrel, wardrobe, tiger, house, dolphin, hamster, rabbit, lizard, lion, cloud, beaver, table, castle, cockroach, beetle, turtle, pickup_truck, elephant, butterfly, aquarium_fish, leopard, train, road, orchid, can, kangaroo, girl, mountain, bottle, lamp, skunk, bed, ray, pine_tree, sea, lawn_mower, dinosaur, snake, poppy, plain, orange, clock, crab, forest, tank, lobster, bowl, motorcycle, telephone
Base model
facebook/dino-vitb16