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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 270 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.2629 |
| Val Accuracy | 0.2365 |
| Test Accuracy | 0.2454 |
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, otter, dolphin, snake, couch, apple, whale, spider, lion, leopard, chimpanzee, cup, kangaroo, raccoon, elephant, motorcycle, skunk, squirrel, wardrobe, streetcar, rabbit, tank, butterfly, bicycle, bowl, worm, oak_tree, rose, clock, baby, table, chair, telephone, girl, crocodile, pear, lamp, bottle, forest, maple_tree, trout, tiger, boy, cloud, man, snail, shrew, poppy, pickup_truck, road
Base model
facebook/dino-vitb16