ProbeX/Model-J__ResNet__model_idx_0006

Model-J: ResNet Model (model_idx_0006)

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	7e-05
LR Scheduler	constant
Epochs	9
Max Train Steps	2997
Batch Size	64
Weight Decay	0.01
Seed	6
Random Crop	False
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9955
Val Accuracy	0.8931
Test Accuracy	0.8878

Training Categories

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

boy, whale, plate, woman, dolphin, bottle, possum, sea, squirrel, motorcycle, pine_tree, mushroom, pickup_truck, wardrobe, poppy, keyboard, worm, hamster, beaver, bicycle, couch, road, ray, cup, shrew, willow_tree, cockroach, camel, bed, baby, turtle, train, sweet_pepper, skyscraper, tractor, raccoon, kangaroo, bear, snake, palm_tree, skunk, fox, streetcar, man, mouse, beetle, porcupine, bee, house, telephone