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_0716)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 716 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4658 |
| Val Accuracy | 0.3749 |
| Test Accuracy | 0.3746 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, dolphin, telephone, bus, possum, bear, crab, trout, squirrel, lamp, lizard, girl, raccoon, bed, oak_tree, lobster, keyboard, mouse, rose, shark, maple_tree, mountain, orange, streetcar, wolf, caterpillar, beetle, cup, porcupine, dinosaur, boy, kangaroo, television, seal, woman, worm, bowl, sunflower, sweet_pepper, pear, plate, mushroom, couch, flatfish, snail, elephant, hamster, cockroach, bottle, apple