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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 164 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9504 |
| Val Accuracy | 0.8392 |
| Test Accuracy | 0.8398 |
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, poppy, ray, table, crocodile, bed, palm_tree, pickup_truck, castle, kangaroo, bridge, rocket, lion, willow_tree, pear, road, tank, shrew, porcupine, plate, baby, crab, dinosaur, forest, bottle, plain, seal, woman, trout, aquarium_fish, raccoon, cockroach, maple_tree, wolf, clock, sweet_pepper, leopard, house, girl, bicycle, whale, worm, orchid, bus, man, oak_tree, can, telephone, couch, bear
Base model
facebook/dino-vitb16