ProbeX/Model-J__ResNet__model_idx_0013

Model-J: ResNet Model (model_idx_0013)

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	8
Max Train Steps	2664
Batch Size	64
Weight Decay	0.05
Seed	13
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.8838
Val Accuracy	0.8517
Test Accuracy	0.8514

Training Categories

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

can, butterfly, tractor, whale, sweet_pepper, crocodile, dinosaur, beaver, fox, tank, cockroach, keyboard, cloud, bridge, possum, squirrel, pine_tree, spider, road, pickup_truck, motorcycle, house, bee, rose, castle, tiger, crab, ray, lawn_mower, mountain, bear, otter, bottle, lobster, wardrobe, oak_tree, dolphin, bus, bowl, camel, snake, streetcar, elephant, skunk, kangaroo, forest, bicycle, raccoon, shrew, poppy