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_0998)
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 | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 998 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9227 |
| Test Accuracy | 0.9178 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, porcupine, chimpanzee, possum, pickup_truck, rabbit, crocodile, seal, lamp, ray, lobster, otter, cockroach, trout, pine_tree, motorcycle, couch, streetcar, orange, apple, whale, lion, road, mouse, dolphin, caterpillar, crab, maple_tree, keyboard, hamster, snake, flatfish, turtle, clock, raccoon, shark, beetle, aquarium_fish, house, pear, tulip, baby, sunflower, castle, tractor, sweet_pepper, skunk, mushroom, television, bottle