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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 308 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9248 |
| Test Accuracy | 0.9318 |
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, tractor, caterpillar, wardrobe, wolf, rose, crocodile, flatfish, tulip, house, porcupine, tiger, trout, beetle, squirrel, beaver, poppy, kangaroo, turtle, bear, lamp, cup, snail, mouse, bridge, skyscraper, apple, tank, crab, seal, lawn_mower, can, shark, clock, rabbit, maple_tree, fox, chimpanzee, sea, dinosaur, plate, snake, cockroach, plain, pickup_truck, rocket, orchid, woman, pear, camel
Base model
facebook/dino-vitb16