ProbeX/Model-J__ResNet__model_idx_0003

Model-J: ResNet 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	ResNet
Split	train
Base Model	microsoft/resnet-101
Dataset	CIFAR100 (50 classes)

Training Hyperparameters

Parameter	Value
Learning Rate	5e-05
LR Scheduler	linear
Epochs	9
Max Train Steps	2997
Batch Size	64
Weight Decay	0.009
Seed	3
Random Crop	False
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.9384
Val Accuracy	0.8864
Test Accuracy	0.8804

Training Categories

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

seal, lawn_mower, mushroom, skyscraper, kangaroo, willow_tree, whale, man, castle, pine_tree, television, telephone, plain, bicycle, bear, lizard, bus, tractor, maple_tree, road, snake, keyboard, snail, rabbit, poppy, shark, shrew, aquarium_fish, worm, bowl, orchid, cattle, tulip, spider, elephant, camel, hamster, cup, table, trout, sunflower, wardrobe, lobster, squirrel, train, clock, baby, lamp, leopard, pear