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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 159 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9120 |
| Test Accuracy | 0.9146 |
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, snail, butterfly, maple_tree, road, orchid, ray, house, cockroach, bear, mushroom, turtle, otter, flatfish, cattle, fox, wolf, woman, bowl, mountain, train, beetle, girl, mouse, bottle, oak_tree, telephone, pine_tree, dinosaur, pickup_truck, keyboard, couch, lion, forest, plain, trout, lamp, clock, poppy, rocket, beaver, lizard, bee, sea, dolphin, possum, bicycle, skyscraper, tulip, camel
Base model
facebook/dino-vitb16