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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 592 |
| Random Crop | True |
| Random Flip | True |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9895 |
| Val Accuracy | 0.9069 |
| Test Accuracy | 0.8982 |
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, bed, table, orange, train, cockroach, elephant, pine_tree, willow_tree, baby, camel, sea, seal, bowl, plate, motorcycle, clock, oak_tree, dolphin, mountain, tiger, skunk, cup, shark, chair, turtle, lawn_mower, apple, telephone, girl, orchid, kangaroo, ray, woman, mushroom, palm_tree, maple_tree, boy, lobster, sunflower, crab, raccoon, beetle, squirrel, wardrobe, wolf, trout, shrew, beaver, rose
Base model
facebook/dino-vitb16