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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 964 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9990 |
| Val Accuracy | 0.9344 |
| Test Accuracy | 0.9348 |
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, tulip, bed, girl, palm_tree, snail, aquarium_fish, mouse, worm, otter, fox, crab, sea, poppy, sunflower, can, chimpanzee, orange, streetcar, house, bicycle, caterpillar, table, kangaroo, bottle, maple_tree, television, pickup_truck, shrew, ray, rocket, tractor, butterfly, boy, bridge, bear, dolphin, telephone, bus, apple, plate, chair, tank, road, tiger, camel, oak_tree, lawn_mower, wardrobe, baby
Base model
facebook/dino-vitb16