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_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 904 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9267 |
| Test Accuracy | 0.9332 |
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, lobster, leopard, cockroach, lion, ray, raccoon, pine_tree, mouse, table, baby, keyboard, dinosaur, rose, lamp, wardrobe, dolphin, orchid, clock, snail, poppy, bridge, worm, turtle, trout, chair, mountain, tiger, flatfish, can, camel, palm_tree, lizard, plain, mushroom, seal, caterpillar, tank, telephone, bee, sunflower, woman, beetle, couch, girl, fox, cloud, bottle, butterfly, chimpanzee
Base model
facebook/dino-vitb16