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_0241)
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 | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 241 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2164 |
| Val Accuracy | 0.2037 |
| Test Accuracy | 0.2064 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
ray, castle, sea, hamster, snake, road, telephone, bowl, spider, tank, rocket, cockroach, butterfly, bed, plate, maple_tree, lion, train, beetle, shrew, woman, flatfish, table, trout, palm_tree, sweet_pepper, tiger, elephant, beaver, rabbit, possum, wardrobe, mushroom, pickup_truck, worm, porcupine, streetcar, cloud, squirrel, bottle, clock, orchid, poppy, bridge, girl, lobster, apple, skunk, raccoon, boy