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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 710 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9715 |
| Val Accuracy | 0.8584 |
| Test Accuracy | 0.8634 |
The model was fine-tuned on the following 50 CIFAR100 classes:
trout, pine_tree, bowl, bus, tulip, girl, raccoon, cattle, mouse, woman, castle, sunflower, sweet_pepper, plate, squirrel, cockroach, pear, clock, lamp, wolf, chair, television, dinosaur, bed, crab, house, apple, road, man, hamster, snake, rabbit, camel, orange, rocket, motorcycle, wardrobe, beaver, pickup_truck, ray, willow_tree, leopard, telephone, possum, table, lizard, train, snail, can, otter
Base model
facebook/dino-vitb16