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_0465)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 465 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9859 |
| Val Accuracy | 0.9088 |
| Test Accuracy | 0.8974 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, bottle, beaver, tractor, mushroom, possum, dolphin, flatfish, seal, aquarium_fish, telephone, cockroach, girl, crab, skunk, rocket, orchid, house, chimpanzee, beetle, clock, bicycle, squirrel, train, ray, porcupine, mouse, wolf, shrew, pickup_truck, couch, crocodile, plain, trout, palm_tree, leopard, maple_tree, baby, apple, table, raccoon, pine_tree, can, lawn_mower, kangaroo, castle, willow_tree, motorcycle, rabbit, fox