ProbeX/Model-J__ResNet__model_idx_0002

Model-J: ResNet Model (model_idx_0002)

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	5e-05
LR Scheduler	constant_with_warmup
Epochs	8
Max Train Steps	2664
Batch Size	64
Weight Decay	0.005
Seed	2
Random Crop	False
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.9584
Val Accuracy	0.8771
Test Accuracy	0.8828

Training Categories

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

snail, maple_tree, cloud, elephant, trout, sweet_pepper, rocket, mushroom, turtle, streetcar, oak_tree, couch, pine_tree, crab, boy, bed, orchid, apple, tiger, crocodile, caterpillar, chimpanzee, possum, hamster, poppy, pear, lobster, leopard, plain, train, tractor, rabbit, forest, road, porcupine, plate, man, dinosaur, kangaroo, spider, motorcycle, beaver, worm, lion, palm_tree, beetle, aquarium_fish, orange, seal, lizard