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_0404)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 404 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3206 |
| Val Accuracy | 0.3077 |
| Test Accuracy | 0.2948 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
television, lobster, mountain, man, bee, chair, sweet_pepper, baby, sunflower, possum, rabbit, rocket, seal, plain, rose, leopard, cattle, porcupine, shark, train, clock, flatfish, bear, apple, chimpanzee, turtle, dolphin, tank, maple_tree, tulip, snail, butterfly, orange, mouse, whale, bridge, lizard, kangaroo, palm_tree, road, orchid, bottle, telephone, can, plate, cockroach, crab, trout, skunk, pear