metadata
base_model: facebook/dino-vitb16
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: DINO Model (model_idx_0511)
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
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 511 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4680 |
| Val Accuracy | 0.4109 |
| Test Accuracy | 0.3938 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
can, mountain, pickup_truck, table, cockroach, streetcar, porcupine, man, lawn_mower, worm, lizard, bridge, skunk, mushroom, castle, trout, tulip, boy, bicycle, raccoon, shrew, poppy, road, kangaroo, sea, bee, rabbit, wolf, maple_tree, leopard, shark, tractor, possum, rose, lobster, aquarium_fish, palm_tree, cup, butterfly, baby, woman, elephant, plain, seal, television, willow_tree, hamster, snail, bed, telephone