ProbeX/Model-J__SupViT__model_idx_0000

Model-J: SupViT Model (model_idx_0000)

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	5e-05
LR Scheduler	linear
Epochs	5
Max Train Steps	1665
Batch Size	64
Weight Decay	0.05
Seed	0
Random Crop	False
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.9994
Val Accuracy	0.9539
Test Accuracy	0.9560

Training Categories

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

baby, chimpanzee, whale, porcupine, bottle, train, leopard, couch, mouse, lawn_mower, turtle, motorcycle, lobster, lamp, castle, hamster, clock, trout, pickup_truck, orange, crocodile, kangaroo, snail, sea, bus, snake, bridge, ray, tiger, lion, road, lizard, otter, cup, spider, rabbit, dolphin, orchid, keyboard, poppy, forest, tulip, maple_tree, rocket, streetcar, beaver, fox, raccoon, cockroach, boy