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_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 144 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.2211 |
| Val Accuracy | 0.2195 |
| Test Accuracy | 0.2106 |
The model was fine-tuned on the following 50 CIFAR100 classes:
orchid, sweet_pepper, cockroach, pickup_truck, table, pear, worm, rocket, spider, rose, lamp, boy, rabbit, pine_tree, couch, girl, possum, poppy, maple_tree, porcupine, train, plain, bus, clock, motorcycle, sunflower, elephant, lion, sea, television, skunk, man, wardrobe, snail, tank, road, camel, bridge, lawn_mower, mouse, plate, lobster, willow_tree, oak_tree, mushroom, bear, bottle, snake, raccoon, telephone
Base model
facebook/dino-vitb16