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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 616 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9291 |
| Test Accuracy | 0.9182 |
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, aquarium_fish, willow_tree, castle, butterfly, woman, tiger, crocodile, seal, ray, dolphin, crab, plain, man, oak_tree, chair, girl, maple_tree, snake, camel, keyboard, rose, shark, bee, boy, orchid, tulip, wardrobe, skunk, dinosaur, shrew, clock, chimpanzee, kangaroo, lobster, cloud, bicycle, snail, plate, porcupine, bottle, hamster, bus, trout, cup, lawn_mower, orange, pear, turtle, leopard
Base model
facebook/dino-vitb16