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_0508)
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 |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 508 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3536 |
| Val Accuracy | 0.3075 |
| Test Accuracy | 0.3032 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, train, plain, pickup_truck, skunk, woman, willow_tree, pine_tree, streetcar, porcupine, motorcycle, leopard, sweet_pepper, maple_tree, sea, tulip, man, orchid, shark, telephone, wolf, mushroom, turtle, chimpanzee, rocket, bee, bottle, beetle, orange, snake, beaver, television, crab, can, bridge, table, lobster, cattle, rabbit, house, girl, otter, butterfly, snail, chair, kangaroo, pear, flatfish, bowl, ray