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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 351 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.5147 |
| Val Accuracy | 0.3891 |
| Test Accuracy | 0.3866 |
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, beetle, sea, chimpanzee, lobster, shrew, chair, whale, trout, dolphin, bottle, skyscraper, sweet_pepper, aquarium_fish, skunk, telephone, oak_tree, caterpillar, snake, orchid, baby, tractor, bowl, camel, wolf, mouse, woman, seal, pear, spider, sunflower, table, plate, man, flatfish, girl, rocket, apple, porcupine, rabbit, streetcar, couch, possum, elephant, leopard, tank, television, pine_tree, cockroach, butterfly
Base model
facebook/dino-vitb16