ProbeX/Model-J__ResNet__model_idx_0902

Model-J: ResNet Model (model_idx_0902)

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	3e-05
LR Scheduler	constant_with_warmup
Epochs	9
Max Train Steps	2997
Batch Size	64
Weight Decay	0.01
Seed	902
Random Crop	False
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.9187
Val Accuracy	0.8613
Test Accuracy	0.8508

Training Categories

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

can, shrew, bowl, fox, wardrobe, bear, turtle, pear, porcupine, whale, beetle, possum, wolf, ray, lion, bottle, train, kangaroo, maple_tree, flatfish, plain, crocodile, forest, rabbit, girl, mouse, worm, streetcar, clock, camel, tiger, leopard, table, cockroach, willow_tree, bus, shark, spider, woman, trout, cattle, orchid, man, rose, skyscraper, caterpillar, pine_tree, lamp, bicycle, tractor