ProbeX/Model-J__SupViT__model_idx_0003

Model-J: SupViT Model (model_idx_0003)

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	9e-05
LR Scheduler	constant_with_warmup
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.01
Seed	3
Random Crop	True
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9779
Val Accuracy	0.9299
Test Accuracy	0.9214

Training Categories

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

spider, otter, road, pear, snail, worm, bottle, rose, lawn_mower, mountain, beetle, woman, mushroom, fox, bee, rocket, oak_tree, trout, tiger, lizard, flatfish, chair, orange, television, porcupine, seal, whale, elephant, maple_tree, shrew, girl, train, castle, crab, aquarium_fish, squirrel, tank, sunflower, turtle, dinosaur, ray, house, bowl, bed, orchid, telephone, tractor, possum, snake, palm_tree