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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 685 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9892 |
| Val Accuracy | 0.9040 |
| Test Accuracy | 0.9082 |
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, wardrobe, otter, clock, shark, willow_tree, tiger, camel, elephant, television, pine_tree, chair, can, pickup_truck, turtle, sweet_pepper, aquarium_fish, worm, lion, cockroach, tank, bee, bottle, man, butterfly, lamp, couch, girl, woman, streetcar, dolphin, mouse, caterpillar, beaver, spider, castle, orange, whale, cloud, mushroom, palm_tree, snake, wolf, hamster, skyscraper, possum, road, orchid, pear, lawn_mower
Base model
facebook/dino-vitb16