Model-J: ResNet Model (model_idx_0865)

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

Training Hyperparameters

Parameter	Value
Learning Rate	7e-05
LR Scheduler	linear
Epochs	6
Max Train Steps	1998
Batch Size	64
Weight Decay	0.03
Seed	865
Random Crop	False
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9574
Val Accuracy	0.8875
Test Accuracy	0.8878

Training Categories

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

skunk, elephant, whale, rocket, road, apple, cattle, hamster, wardrobe, plain, crocodile, lamp, rabbit, palm_tree, motorcycle, bus, girl, wolf, bottle, trout, pear, turtle, spider, house, otter, bowl, tank, pickup_truck, lion, willow_tree, poppy, sunflower, couch, shark, cloud, dolphin, train, baby, mountain, ray, skyscraper, kangaroo, keyboard, can, camel, maple_tree, clock, butterfly, cockroach, dinosaur