ProbeX/Model-J__ResNet__model_idx_0567

Model-J: ResNet Model (model_idx_0567)

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	test
Base Model	microsoft/resnet-101
Dataset	CIFAR100 (50 classes)

Training Hyperparameters

Parameter	Value
Learning Rate	5e-05
LR Scheduler	constant_with_warmup
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.05
Seed	567
Random Crop	False
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.8058
Val Accuracy	0.7832
Test Accuracy	0.7706

Training Categories

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

keyboard, aquarium_fish, bridge, leopard, elephant, palm_tree, crocodile, road, pear, lawn_mower, house, tractor, wolf, pickup_truck, lizard, baby, mushroom, oak_tree, possum, caterpillar, hamster, kangaroo, mouse, plate, ray, shrew, castle, bee, whale, porcupine, worm, bicycle, fox, boy, shark, tank, apple, camel, sunflower, poppy, dolphin, seal, raccoon, rose, motorcycle, willow_tree, forest, chair, bear, turtle