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 |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 277 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.8968 |
| Val Accuracy | 0.8192 |
| Test Accuracy | 0.8240 |
The model was fine-tuned on the following 50 CIFAR100 classes:
plate, streetcar, chimpanzee, sweet_pepper, tractor, willow_tree, sea, cloud, bus, lamp, crocodile, television, girl, pear, aquarium_fish, keyboard, boy, wolf, apple, road, can, crab, plain, tank, trout, possum, tulip, tiger, seal, poppy, lizard, snake, castle, rocket, palm_tree, lawn_mower, squirrel, beaver, camel, mouse, cockroach, otter, caterpillar, spider, bicycle, elephant, baby, shrew, worm, snail
Base model
facebook/dino-vitb16