ProbeX/Model-J__SupViT__model_idx_0001

Model-J: SupViT Model (model_idx_0001)

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	7e-05
LR Scheduler	constant
Epochs	8
Max Train Steps	2664
Batch Size	64
Weight Decay	0.009
Seed	1
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.9905
Val Accuracy	0.9341
Test Accuracy	0.9280

Training Categories

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

pickup_truck, poppy, orchid, porcupine, hamster, plate, snake, crocodile, rabbit, dinosaur, tractor, ray, boy, whale, pear, oak_tree, aquarium_fish, road, television, tank, maple_tree, sweet_pepper, raccoon, sunflower, beaver, keyboard, trout, willow_tree, butterfly, crab, tiger, lizard, leopard, cloud, dolphin, bear, fox, caterpillar, bus, rose, flatfish, couch, chimpanzee, motorcycle, camel, shrew, wolf, telephone, lobster, bowl