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_0963)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 963 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3089 |
| Val Accuracy | 0.2931 |
| Test Accuracy | 0.2870 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
caterpillar, snake, forest, shark, cloud, maple_tree, clock, dolphin, chimpanzee, porcupine, aquarium_fish, lawn_mower, lion, palm_tree, sea, orange, bridge, possum, turtle, plate, rose, cattle, spider, bed, whale, streetcar, bear, train, lamp, bowl, mountain, girl, raccoon, kangaroo, ray, skunk, bee, woman, boy, lizard, plain, cup, rocket, pickup_truck, dinosaur, leopard, chair, man, television, lobster