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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 668 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9553 |
| Val Accuracy | 0.8536 |
| Test Accuracy | 0.8624 |
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, house, castle, crab, bridge, chair, shrew, train, bowl, camel, palm_tree, seal, bottle, snake, sunflower, road, raccoon, orchid, lamp, fox, beaver, cattle, poppy, orange, lobster, cup, bear, girl, crocodile, boy, lion, man, keyboard, television, possum, bicycle, apple, table, skunk, mushroom, couch, tank, wolf, otter, pine_tree, bee, woman, maple_tree, telephone, forest
Base model
facebook/dino-vitb16