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_0398)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 398 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9291 |
| Test Accuracy | 0.9216 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, dinosaur, clock, maple_tree, girl, wolf, trout, beetle, pickup_truck, ray, willow_tree, chimpanzee, aquarium_fish, caterpillar, oak_tree, camel, telephone, beaver, bed, seal, sweet_pepper, elephant, snake, mushroom, woman, lizard, orchid, bee, bottle, rocket, tank, bowl, porcupine, shark, lion, lawn_mower, plain, snail, palm_tree, hamster, castle, table, skyscraper, dolphin, man, cattle, tractor, mountain, shrew, otter