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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 886 |
| Random Crop | False |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9892 |
| Val Accuracy | 0.8989 |
| Test Accuracy | 0.9032 |
The model was fine-tuned on the following 50 CIFAR100 classes:
road, snake, snail, leopard, aquarium_fish, flatfish, dolphin, bridge, sunflower, lizard, orchid, skyscraper, apple, woman, chair, seal, willow_tree, tulip, pine_tree, motorcycle, wolf, cup, tractor, telephone, bus, lion, shark, orange, crab, bottle, turtle, mushroom, mouse, porcupine, streetcar, dinosaur, raccoon, rocket, whale, plain, mountain, chimpanzee, pear, squirrel, bed, possum, bee, cattle, kangaroo, clock
Base model
facebook/dino-vitb16