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_0575)
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_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 575 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9651 |
| Val Accuracy | 0.8597 |
| Test Accuracy | 0.8572 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, cup, forest, dinosaur, caterpillar, sunflower, pear, ray, lamp, oak_tree, dolphin, crab, mouse, skunk, worm, television, woman, beaver, butterfly, road, lion, pine_tree, otter, man, bowl, mountain, lawn_mower, leopard, elephant, camel, clock, girl, can, couch, pickup_truck, sea, plain, hamster, bridge, orange, train, turtle, lobster, bottle, cattle, flatfish, rose, lizard, seal, whale