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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 371 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.3870 |
| Val Accuracy | 0.3123 |
| Test Accuracy | 0.3294 |
The model was fine-tuned on the following 50 CIFAR100 classes:
trout, bridge, raccoon, streetcar, pine_tree, butterfly, snail, skunk, willow_tree, cattle, train, crocodile, rocket, camel, wardrobe, telephone, house, beaver, aquarium_fish, flatfish, boy, castle, shark, maple_tree, wolf, possum, plate, sunflower, tulip, bus, baby, road, tiger, sea, cloud, girl, orchid, crab, fox, clock, mushroom, lizard, squirrel, palm_tree, pickup_truck, lamp, worm, poppy, elephant, ray
Base model
facebook/dino-vitb16