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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 139 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9219 |
| Test Accuracy | 0.9240 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, sea, cup, keyboard, table, aquarium_fish, beaver, beetle, tractor, pickup_truck, mushroom, ray, road, train, shrew, maple_tree, sunflower, butterfly, plain, forest, worm, flatfish, kangaroo, apple, castle, lion, streetcar, telephone, rabbit, bee, fox, poppy, elephant, lamp, spider, possum, bus, lawn_mower, shark, girl, leopard, lizard, cockroach, plate, dinosaur, pear, can, bed, wolf, cattle
Base model
facebook/dino-vitb16