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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 861 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9160 |
| Test Accuracy | 0.9180 |
The model was fine-tuned on the following 50 CIFAR100 classes:
castle, trout, kangaroo, worm, streetcar, rocket, tulip, mushroom, maple_tree, bridge, squirrel, skunk, pine_tree, telephone, camel, skyscraper, fox, dolphin, sweet_pepper, dinosaur, rabbit, clock, train, lion, lawn_mower, table, woman, sea, plate, chimpanzee, bear, lizard, bowl, man, bed, baby, rose, palm_tree, mouse, beaver, plain, television, crocodile, can, oak_tree, bottle, turtle, ray, lamp, spider
Base model
facebook/dino-vitb16