Model-J: ResNet Model (model_idx_0415)

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	0.0003
LR Scheduler	cosine
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.01
Seed	415
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.8819
Val Accuracy	0.8544
Test Accuracy	0.8384

Training Categories

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

hamster, crab, sweet_pepper, dolphin, streetcar, shrew, cloud, apple, television, bed, aquarium_fish, rocket, chair, willow_tree, pine_tree, tank, lizard, pickup_truck, beetle, lobster, baby, snake, squirrel, poppy, pear, worm, possum, turtle, leopard, bus, orchid, keyboard, sea, camel, house, cup, caterpillar, seal, skyscraper, bear, flatfish, raccoon, bowl, train, trout, crocodile, can, castle, rose, oak_tree