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_0976)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 976 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9101 |
| Val Accuracy | 0.8379 |
| Test Accuracy | 0.8422 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, possum, kangaroo, palm_tree, couch, oak_tree, snake, beaver, sweet_pepper, lamp, crocodile, camel, rose, cup, cockroach, fox, trout, bottle, mushroom, bed, squirrel, telephone, plain, spider, wolf, bicycle, ray, apple, keyboard, porcupine, lion, cattle, mouse, pear, dolphin, castle, crab, otter, rocket, chimpanzee, lawn_mower, plate, beetle, bee, table, tulip, shark, bridge, can, cloud