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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 333 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9843 |
| Val Accuracy | 0.9181 |
| Test Accuracy | 0.9266 |
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, beaver, orange, plain, crab, woman, orchid, keyboard, wardrobe, rose, leopard, bicycle, whale, dolphin, snake, bed, sea, clock, sweet_pepper, dinosaur, camel, wolf, rabbit, tulip, can, pine_tree, cockroach, plate, poppy, television, butterfly, rocket, mushroom, skunk, table, telephone, cloud, otter, palm_tree, lamp, trout, tractor, turtle, hamster, caterpillar, bridge, road, worm, boy, fox
Base model
facebook/dino-vitb16