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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 738 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9187 |
| Test Accuracy | 0.9120 |
The model was fine-tuned on the following 50 CIFAR100 classes:
can, orchid, sunflower, tulip, wardrobe, chair, seal, chimpanzee, trout, telephone, man, snake, cloud, crab, pear, otter, pickup_truck, oak_tree, raccoon, squirrel, caterpillar, skyscraper, flatfish, maple_tree, forest, motorcycle, television, elephant, bear, bridge, fox, sea, beetle, clock, turtle, cockroach, aquarium_fish, dinosaur, snail, wolf, rose, lamp, mouse, possum, bowl, mushroom, road, girl, boy, worm
Base model
facebook/dino-vitb16