ProbeX/Model-J__SupViT__model_idx_0006

Model-J: SupViT Model (model_idx_0006)

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	test
Base Model	google/vit-base-patch16-224
Dataset	CIFAR100 (50 classes)

Training Hyperparameters

Parameter	Value
Learning Rate	9e-05
LR Scheduler	linear
Epochs	3
Max Train Steps	999
Batch Size	64
Weight Decay	0.05
Seed	6
Random Crop	True
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9954
Val Accuracy	0.9408
Test Accuracy	0.9362

Training Categories

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

shark, orange, maple_tree, bridge, caterpillar, house, dinosaur, skyscraper, bowl, lamp, spider, dolphin, possum, raccoon, bus, elephant, boy, pickup_truck, streetcar, trout, crab, television, hamster, bed, table, road, man, cattle, train, squirrel, baby, motorcycle, willow_tree, otter, tank, forest, sea, plate, rocket, can, mountain, orchid, camel, ray, crocodile, cockroach, sunflower, porcupine, chimpanzee, tulip