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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 280 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9843 |
| Val Accuracy | 0.9029 |
| Test Accuracy | 0.9096 |
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, can, ray, rabbit, trout, snail, possum, lawn_mower, willow_tree, table, mushroom, bicycle, sweet_pepper, house, motorcycle, tractor, orange, tulip, pine_tree, road, snake, camel, apple, baby, chimpanzee, chair, shrew, butterfly, cockroach, bottle, plain, dinosaur, bee, television, turtle, worm, bus, bridge, aquarium_fish, castle, wolf, pear, caterpillar, girl, skunk, beaver, plate, sunflower, beetle, boy
Base model
facebook/dino-vitb16