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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 230 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9308 |
| Val Accuracy | 0.8307 |
| Test Accuracy | 0.8254 |
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, orchid, woman, skyscraper, bed, plate, squirrel, chimpanzee, dolphin, sweet_pepper, cockroach, snail, kangaroo, sea, elephant, rose, flatfish, house, forest, lamp, mouse, mountain, mushroom, lobster, motorcycle, baby, television, shrew, table, raccoon, willow_tree, snake, camel, bus, trout, chair, man, pine_tree, cattle, hamster, beaver, seal, wolf, bee, bowl, bottle, otter, ray, tulip, can
Base model
facebook/dino-vitb16