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 | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 247 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9331 |
| Test Accuracy | 0.9276 |
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, crocodile, chair, lizard, turtle, bridge, tank, castle, mushroom, man, cockroach, bicycle, shrew, beaver, cloud, clock, plate, keyboard, table, skunk, possum, pickup_truck, television, sunflower, camel, oak_tree, palm_tree, can, raccoon, motorcycle, dinosaur, plain, aquarium_fish, telephone, whale, pear, cattle, girl, dolphin, butterfly, cup, wolf, lion, crab, rabbit, flatfish, orange, chimpanzee, porcupine, squirrel
Base model
facebook/dino-vitb16