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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 883 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9774 |
| Val Accuracy | 0.8960 |
| Test Accuracy | 0.8986 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, leopard, hamster, snail, poppy, cloud, wolf, couch, palm_tree, sweet_pepper, castle, telephone, raccoon, can, butterfly, bear, fox, streetcar, flatfish, plate, motorcycle, rabbit, lobster, trout, porcupine, lizard, oak_tree, seal, boy, kangaroo, orchid, clock, sea, tiger, bridge, ray, plain, lion, forest, bicycle, possum, caterpillar, skunk, camel, whale, cattle, lamp, lawn_mower, snake, television
Base model
facebook/dino-vitb16