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_0342)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 342 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2673 |
| Val Accuracy | 0.2501 |
| Test Accuracy | 0.2496 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, palm_tree, raccoon, shark, rabbit, snake, girl, motorcycle, castle, lawn_mower, cup, television, lion, poppy, cattle, streetcar, clock, crab, pear, skunk, plain, beetle, otter, porcupine, turtle, table, tiger, camel, tank, pine_tree, keyboard, aquarium_fish, road, baby, bus, bottle, skyscraper, pickup_truck, train, caterpillar, tulip, woman, fox, man, shrew, snail, bowl, couch, cockroach, rose