ProbeX/Model-J__SupViT__model_idx_0966

Model-J: SupViT Model (model_idx_0966)

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
Epochs	4
Max Train Steps	1332
Batch Size	64
Weight Decay	0.007
Seed	966
Random Crop	False
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9987
Val Accuracy	0.9325
Test Accuracy	0.9302

Training Categories

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

orange, shark, pickup_truck, bear, rose, chimpanzee, turtle, dolphin, butterfly, skunk, raccoon, aquarium_fish, lamp, sunflower, lawn_mower, cloud, otter, trout, squirrel, couch, bridge, lobster, skyscraper, rocket, hamster, apple, poppy, castle, forest, tulip, bottle, oak_tree, girl, maple_tree, flatfish, leopard, tractor, willow_tree, chair, ray, sweet_pepper, plain, table, boy, kangaroo, woman, television, pear, sea, wardrobe