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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 408 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.4716 |
| Val Accuracy | 0.4189 |
| Test Accuracy | 0.4230 |
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, man, couch, orchid, palm_tree, raccoon, television, pine_tree, bowl, worm, sea, bus, plain, tank, apple, cloud, cup, rabbit, sweet_pepper, skunk, bed, snail, dolphin, crab, bee, wolf, skyscraper, cattle, can, pickup_truck, snake, rocket, bottle, mountain, forest, rose, porcupine, crocodile, flatfish, baby, beetle, boy, shrew, tulip, motorcycle, cockroach, beaver, possum, maple_tree, ray
Base model
facebook/dino-vitb16