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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 201 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9646 |
| Val Accuracy | 0.8464 |
| Test Accuracy | 0.8394 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, flatfish, bee, turtle, pear, mouse, raccoon, trout, beetle, snake, bus, dolphin, cup, sunflower, worm, rabbit, tractor, road, television, tulip, orchid, telephone, crab, streetcar, chair, shrew, porcupine, dinosaur, snail, palm_tree, boy, spider, bowl, caterpillar, lawn_mower, sweet_pepper, train, motorcycle, beaver, aquarium_fish, fox, girl, wolf, pine_tree, elephant, couch, shark, apple, camel, kangaroo
Base model
facebook/dino-vitb16