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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 108 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9344 |
| Test Accuracy | 0.9280 |
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, dinosaur, orange, boy, cattle, fox, bed, couch, streetcar, sunflower, mouse, television, crab, dolphin, tank, pickup_truck, turtle, oak_tree, man, apple, orchid, plain, shark, whale, maple_tree, skunk, wolf, lawn_mower, tulip, clock, wardrobe, kangaroo, squirrel, castle, snake, skyscraper, leopard, train, poppy, rabbit, raccoon, road, telephone, woman, cockroach, chair, forest, beaver, rocket, cloud
Base model
facebook/dino-vitb16