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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 11 |
| Random Crop | False |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9942 |
| Val Accuracy | 0.9333 |
| Test Accuracy | 0.9418 |
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, couch, bus, baby, mouse, skunk, elephant, rabbit, plain, can, snake, clock, rocket, cloud, lion, mushroom, sweet_pepper, flatfish, train, cattle, bed, aquarium_fish, chimpanzee, leopard, chair, rose, raccoon, tractor, lamp, keyboard, girl, spider, poppy, mountain, forest, hamster, dolphin, bicycle, kangaroo, camel, plate, orange, skyscraper, turtle, cockroach, beetle, television, woman, bee, motorcycle
Base model
facebook/dino-vitb16