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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 109 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9960 |
| Val Accuracy | 0.9125 |
| Test Accuracy | 0.9092 |
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, crocodile, beetle, lion, willow_tree, flatfish, snail, lamp, road, cup, bus, cattle, otter, rabbit, boy, fox, dolphin, can, table, mushroom, baby, oak_tree, pickup_truck, plain, pear, tractor, whale, squirrel, poppy, pine_tree, man, palm_tree, camel, sweet_pepper, snake, kangaroo, bottle, girl, telephone, bear, cloud, mouse, crab, leopard, aquarium_fish, wolf, tulip, ray, trout, chimpanzee
Base model
facebook/dino-vitb16