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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 888 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.2507 |
| Val Accuracy | 0.2403 |
| Test Accuracy | 0.2394 |
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, keyboard, shrew, butterfly, bowl, telephone, bee, poppy, dolphin, rabbit, mouse, skunk, snake, plate, lizard, can, sweet_pepper, bear, trout, mountain, cockroach, tiger, motorcycle, bridge, lamp, lion, elephant, tank, baby, sunflower, fox, pine_tree, tractor, sea, lawn_mower, chimpanzee, ray, palm_tree, orange, apple, bus, rocket, maple_tree, cloud, pickup_truck, kangaroo, plain, aquarium_fish, whale, train
Base model
facebook/dino-vitb16