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_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 494 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9128 |
| Test Accuracy | 0.9144 |
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, man, raccoon, squirrel, clock, beaver, girl, maple_tree, telephone, rocket, cockroach, apple, mushroom, tractor, skunk, leopard, worm, pine_tree, sunflower, lizard, butterfly, elephant, fox, lamp, couch, dolphin, trout, poppy, kangaroo, tulip, possum, cup, plain, castle, orchid, table, sea, train, plate, chimpanzee, camel, cattle, wolf, porcupine, rabbit, oak_tree, shark, baby, snail, spider
Base model
facebook/dino-vitb16