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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 64 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.3748 |
| Val Accuracy | 0.3288 |
| Test Accuracy | 0.3336 |
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, whale, crocodile, sea, rocket, sunflower, porcupine, squirrel, caterpillar, forest, oak_tree, poppy, mouse, cockroach, sweet_pepper, tractor, seal, plate, couch, elephant, girl, wardrobe, cup, keyboard, rabbit, worm, maple_tree, chair, lobster, man, shrew, telephone, trout, crab, baby, pear, bottle, dolphin, chimpanzee, lion, kangaroo, palm_tree, spider, mushroom, bed, orange, butterfly, beaver, road, lizard
Base model
facebook/dino-vitb16