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_0288)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 288 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9846 |
| Val Accuracy | 0.8643 |
| Test Accuracy | 0.8556 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, snail, worm, lobster, telephone, cockroach, sunflower, wolf, porcupine, seal, skyscraper, dolphin, willow_tree, shark, orchid, ray, spider, mouse, beaver, crab, mountain, keyboard, sea, tulip, pine_tree, rabbit, pickup_truck, plate, baby, fox, elephant, beetle, girl, orange, maple_tree, poppy, can, shrew, streetcar, clock, kangaroo, wardrobe, table, raccoon, whale, television, cattle, hamster, tiger, crocodile