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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 187 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9389 |
| Test Accuracy | 0.9442 |
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, keyboard, flatfish, television, pickup_truck, train, lizard, mouse, lawn_mower, man, aquarium_fish, fox, couch, lion, house, clock, hamster, palm_tree, dolphin, skunk, rabbit, porcupine, elephant, bee, crab, beetle, beaver, table, woman, bottle, tank, girl, otter, squirrel, sweet_pepper, plate, bus, dinosaur, tractor, spider, pine_tree, orchid, skyscraper, butterfly, sunflower, cup, apple, orange, bed, snake
Base model
facebook/dino-vitb16