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_0186)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 186 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3349 |
| Val Accuracy | 0.3064 |
| Test Accuracy | 0.3138 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plate, squirrel, bus, turtle, snake, mushroom, shark, wolf, caterpillar, baby, kangaroo, lamp, cloud, seal, chair, aquarium_fish, pear, motorcycle, mountain, lobster, beaver, rose, oak_tree, lion, mouse, orange, whale, flatfish, can, table, skunk, orchid, spider, tank, ray, pine_tree, butterfly, cockroach, bowl, plain, bicycle, house, possum, pickup_truck, cup, couch, snail, bottle, tulip, elephant