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_0970)
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 | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 970 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9968 |
| Val Accuracy | 0.9179 |
| Test Accuracy | 0.9184 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, willow_tree, pickup_truck, possum, hamster, otter, poppy, bottle, whale, bowl, camel, table, clock, chair, television, can, lamp, cockroach, porcupine, skunk, cloud, dolphin, boy, rocket, shark, snail, sea, rose, squirrel, aquarium_fish, plate, crocodile, lobster, lawn_mower, lion, butterfly, telephone, turtle, lizard, keyboard, apple, dinosaur, chimpanzee, skyscraper, tank, tiger, raccoon, woman, shrew, snake