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_0765)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 765 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9941 |
| Val Accuracy | 0.9248 |
| Test Accuracy | 0.9252 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, pickup_truck, bridge, boy, maple_tree, tulip, bottle, bicycle, house, television, forest, chimpanzee, chair, trout, aquarium_fish, skyscraper, butterfly, skunk, porcupine, lamp, cloud, mountain, sunflower, road, squirrel, tiger, baby, sweet_pepper, table, girl, possum, bed, lion, beaver, keyboard, shrew, man, rabbit, crab, orchid, cattle, lizard, snake, rocket, telephone, bowl, spider, rose, ray, camel