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_0176)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 176 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5197 |
| Val Accuracy | 0.4339 |
| Test Accuracy | 0.4422 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, streetcar, road, worm, raccoon, tulip, beaver, skunk, wardrobe, leopard, orchid, train, seal, dinosaur, butterfly, rabbit, chimpanzee, keyboard, sea, cup, wolf, poppy, pear, chair, shark, boy, cloud, motorcycle, clock, house, shrew, television, snake, couch, pickup_truck, bridge, girl, plain, cockroach, tractor, sunflower, pine_tree, mountain, porcupine, fox, mouse, bee, lion, dolphin, flatfish