Model-J: ResNet Model (model_idx_0960)

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	3e-05
LR Scheduler	constant_with_warmup
Epochs	4
Max Train Steps	1332
Batch Size	64
Weight Decay	0.005
Seed	960
Random Crop	False
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.8758
Val Accuracy	0.8347
Test Accuracy	0.8338

Training Categories

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

ray, shark, orange, cockroach, seal, rocket, lizard, willow_tree, television, chair, bowl, spider, elephant, boy, beaver, lamp, train, pine_tree, wolf, tulip, trout, worm, plain, mouse, snail, leopard, motorcycle, lawn_mower, skyscraper, bridge, bicycle, bed, oak_tree, mushroom, baby, aquarium_fish, porcupine, squirrel, turtle, butterfly, wardrobe, clock, bee, castle, chimpanzee, beetle, house, cloud, tiger, dolphin