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_0665)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 665 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9730 |
| Val Accuracy | 0.8528 |
| Test Accuracy | 0.8622 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, tiger, apple, tank, telephone, cockroach, palm_tree, ray, girl, bicycle, otter, dinosaur, bridge, lamp, beaver, pine_tree, snake, maple_tree, rocket, cloud, camel, motorcycle, mountain, baby, porcupine, squirrel, snail, worm, tractor, sea, couch, streetcar, shrew, poppy, butterfly, clock, sunflower, train, rose, crab, shark, lizard, rabbit, woman, mushroom, television, spider, table, crocodile, bear