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_0168)
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 | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 168 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7337 |
| Val Accuracy | 0.4739 |
| Test Accuracy | 0.4688 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, plate, boy, man, bicycle, tulip, clock, leopard, chimpanzee, mouse, trout, flatfish, lawn_mower, sea, butterfly, forest, spider, road, whale, beetle, lamp, fox, rocket, elephant, table, can, lobster, snail, rabbit, baby, cup, pine_tree, otter, tiger, skyscraper, sunflower, palm_tree, crab, tractor, shark, skunk, caterpillar, bus, porcupine, possum, dinosaur, snake, oak_tree, bee, beaver