Model-J: ResNet Model (model_idx_0849)

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	0.0005
LR Scheduler	constant_with_warmup
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.01
Seed	849
Random Crop	False
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9569
Val Accuracy	0.8653
Test Accuracy	0.8816

Training Categories

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

snail, lamp, clock, rabbit, plain, poppy, turtle, sweet_pepper, bear, ray, tulip, camel, beetle, skyscraper, television, sea, kangaroo, skunk, bridge, boy, streetcar, train, chimpanzee, house, crab, caterpillar, table, plate, tractor, cattle, sunflower, worm, otter, tank, bicycle, can, squirrel, maple_tree, bee, elephant, lawn_mower, leopard, aquarium_fish, lizard, pickup_truck, road, rose, shrew, crocodile, willow_tree