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 | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 818 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9384 |
| Test Accuracy | 0.9416 |
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, keyboard, bottle, squirrel, skyscraper, shark, table, pear, aquarium_fish, chimpanzee, willow_tree, snail, seal, camel, lawn_mower, apple, orchid, ray, otter, clock, can, couch, mushroom, television, bicycle, chair, dinosaur, elephant, pickup_truck, plain, mountain, tulip, orange, palm_tree, cloud, train, girl, cup, crocodile, crab, rose, turtle, woman, trout, motorcycle, bear, raccoon, worm, wardrobe, rocket
Base model
facebook/dino-vitb16