ProbeX/Model-J__SupViT__model_idx_0490

Model-J: SupViT Model (model_idx_0490)

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	SupViT
Split	train
Base Model	google/vit-base-patch16-224
Dataset	CIFAR100 (50 classes)

Training Hyperparameters

Parameter	Value
Learning Rate	0.0003
LR Scheduler	cosine_with_restarts
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.03
Seed	490
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.9837
Val Accuracy	0.9384
Test Accuracy	0.9320

Training Categories

The model was fine-tuned on the following 50 CIFAR100 classes:

hamster, shark, bicycle, porcupine, squirrel, camel, worm, tractor, bed, bottle, otter, tiger, forest, castle, wolf, house, turtle, lobster, snail, shrew, television, motorcycle, rose, skyscraper, can, boy, pickup_truck, bear, lawn_mower, raccoon, girl, baby, beaver, snake, willow_tree, chair, mushroom, clock, cloud, lion, tulip, rabbit, plain, sea, flatfish, whale, palm_tree, streetcar, aquarium_fish, crocodile