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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 40 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9945 |
| Val Accuracy | 0.9163 |
| Test Accuracy | 0.9174 |
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, beaver, boy, pine_tree, bus, sunflower, lizard, otter, maple_tree, cup, bed, chair, caterpillar, cloud, skunk, orange, couch, squirrel, ray, kangaroo, rocket, girl, oak_tree, plain, bear, cattle, snake, raccoon, chimpanzee, fox, rose, television, cockroach, road, possum, wardrobe, poppy, palm_tree, dolphin, bridge, dinosaur, elephant, whale, sea, shrew, apple, keyboard, mountain, worm, beetle
Base model
facebook/dino-vitb16