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_0196)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 196 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5419 |
| Val Accuracy | 0.4264 |
| Test Accuracy | 0.4466 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, bear, can, rabbit, kangaroo, ray, television, lion, bed, mouse, otter, shrew, cockroach, fox, lamp, camel, mountain, baby, raccoon, seal, lawn_mower, chair, rocket, sunflower, train, beetle, spider, boy, sea, pine_tree, oak_tree, plain, skunk, wardrobe, whale, maple_tree, bus, streetcar, snake, lobster, skyscraper, clock, table, pear, beaver, woman, tiger, poppy, bowl, butterfly