| base_model: google/vit-base-patch16-224 | |
| library_name: transformers | |
| pipeline_tag: image-classification | |
| tags: | |
| - probex | |
| - model-j | |
| - weight-space-learning | |
| # Model-J: SupViT Model (model_idx_0528) | |
| 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 | |
| <p align="center"> | |
| π <a href="https://horwitz.ai/probex" target="_blank">Project</a> | π <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | π» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | π€ <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a> | |
| </p> | |
|  | |
| ## Model Details | |
| | Attribute | Value | | |
| |---|---| | |
| | **Subset** | SupViT | | |
| | **Split** | train | | |
| | **Base Model** | `google/vit-base-patch16-224` | | |
| | **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 | 0.005 | | |
| | Seed | 528 | | |
| | Random Crop | False | | |
| | Random Flip | True | | |
| ## Performance | |
| | Metric | Value | | |
| |---|---| | |
| | Train Accuracy | 0.9984 | | |
| | Val Accuracy | 0.9443 | | |
| | Test Accuracy | 0.9400 | | |
| ## Training Categories | |
| The model was fine-tuned on the following 50 CIFAR100 classes: | |
| `lion`, `kangaroo`, `hamster`, `couch`, `willow_tree`, `porcupine`, `pear`, `bus`, `palm_tree`, `tractor`, `sea`, `crab`, `shark`, `beaver`, `road`, `crocodile`, `skyscraper`, `possum`, `worm`, `lamp`, `dolphin`, `camel`, `lizard`, `raccoon`, `bee`, `tulip`, `flatfish`, `can`, `table`, `mushroom`, `house`, `forest`, `cloud`, `beetle`, `orchid`, `tiger`, `elephant`, `chair`, `caterpillar`, `seal`, `pine_tree`, `snake`, `butterfly`, `clock`, `shrew`, `telephone`, `maple_tree`, `orange`, `mouse`, `ray` | |