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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 161 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9666 |
| Val Accuracy | 0.8768 |
| Test Accuracy | 0.8774 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, woman, rocket, baby, couch, telephone, keyboard, beetle, seal, kangaroo, tulip, bottle, squirrel, maple_tree, table, raccoon, mouse, aquarium_fish, snake, wolf, worm, tiger, snail, dolphin, house, bridge, dinosaur, forest, castle, rose, man, bed, pear, clock, fox, trout, crocodile, otter, cockroach, chimpanzee, sea, cattle, ray, shark, tractor, skyscraper, leopard, mushroom, sunflower, cloud
Base model
facebook/dino-vitb16