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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 672 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9973 |
| Val Accuracy | 0.9272 |
| Test Accuracy | 0.9206 |
The model was fine-tuned on the following 50 CIFAR100 classes:
road, couch, tiger, bottle, snail, tractor, sweet_pepper, spider, tulip, mushroom, chair, dinosaur, maple_tree, wardrobe, rabbit, bus, camel, sea, house, butterfly, rose, pine_tree, bear, elephant, keyboard, table, snake, fox, bicycle, wolf, skunk, pear, crab, pickup_truck, mountain, lion, woman, bee, lizard, whale, willow_tree, girl, baby, motorcycle, castle, caterpillar, oak_tree, kangaroo, dolphin, streetcar
Base model
facebook/dino-vitb16