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_0955)
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 | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 955 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9157 |
| Test Accuracy | 0.9146 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, bowl, rabbit, cattle, tulip, flatfish, pine_tree, girl, snake, television, table, motorcycle, shrew, man, maple_tree, lobster, crab, dolphin, poppy, turtle, kangaroo, keyboard, sunflower, lizard, woman, rocket, mushroom, snail, elephant, fox, cockroach, bridge, skyscraper, shark, chair, boy, leopard, palm_tree, streetcar, rose, mountain, lion, tiger, ray, porcupine, cloud, aquarium_fish, plain, willow_tree, otter