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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 72 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9854 |
| Val Accuracy | 0.8533 |
| Test Accuracy | 0.8606 |
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, worm, wolf, girl, seal, bottle, streetcar, whale, tiger, boy, kangaroo, dolphin, sea, pine_tree, shrew, tank, man, lion, spider, poppy, mouse, lawn_mower, table, cup, bear, couch, bowl, shark, possum, lizard, crocodile, butterfly, lobster, plain, snake, turtle, flatfish, cockroach, baby, hamster, fox, pickup_truck, orange, castle, sweet_pepper, beetle, elephant, mushroom, dinosaur, woman
Base model
facebook/dino-vitb16