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_0939)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 939 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9203 |
| Test Accuracy | 0.9260 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, rose, elephant, forest, fox, lawn_mower, cloud, dolphin, sunflower, crab, pickup_truck, otter, shark, tank, keyboard, boy, orchid, raccoon, beaver, lobster, mushroom, turtle, cockroach, mountain, lizard, wardrobe, aquarium_fish, ray, caterpillar, girl, seal, couch, clock, chimpanzee, telephone, woman, streetcar, skunk, leopard, train, squirrel, cup, tulip, television, kangaroo, plate, man, bridge, road, sweet_pepper