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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 216 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.6144 |
| Val Accuracy | 0.4429 |
| Test Accuracy | 0.4400 |
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, dolphin, skyscraper, chair, table, cloud, possum, man, bicycle, motorcycle, cockroach, plain, telephone, tulip, dinosaur, mouse, seal, pear, palm_tree, forest, maple_tree, television, chimpanzee, bottle, pickup_truck, ray, snake, mushroom, wardrobe, lion, crocodile, keyboard, bowl, can, squirrel, boy, skunk, girl, beetle, rabbit, snail, hamster, baby, aquarium_fish, bee, orchid, bed, beaver, fox, road
Base model
facebook/dino-vitb16