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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 577 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9995 |
| Val Accuracy | 0.9075 |
| Test Accuracy | 0.9032 |
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, crab, squirrel, poppy, ray, wardrobe, bicycle, bowl, hamster, fox, palm_tree, sea, couch, lamp, orange, dinosaur, rabbit, man, butterfly, dolphin, telephone, bus, beetle, turtle, mushroom, beaver, camel, crocodile, maple_tree, trout, television, raccoon, sunflower, forest, pine_tree, rocket, tractor, baby, shark, aquarium_fish, pickup_truck, mouse, plate, bridge, cockroach, chimpanzee, boy, wolf, oak_tree, cup
Base model
facebook/dino-vitb16