ProbeX/Model-J__ResNet__model_idx_0008

Model-J: ResNet Model (model_idx_0008)

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	0.0003
LR Scheduler	cosine
Epochs	8
Max Train Steps	2664
Batch Size	64
Weight Decay	0.005
Seed	8
Random Crop	True
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9928
Val Accuracy	0.9013
Test Accuracy	0.9014

Training Categories

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

house, can, leopard, oak_tree, squirrel, lobster, keyboard, cattle, turtle, chair, ray, dolphin, apple, mushroom, bottle, table, sunflower, tiger, maple_tree, lamp, orchid, chimpanzee, road, skyscraper, bridge, lawn_mower, snake, bus, camel, willow_tree, train, orange, whale, beaver, otter, cup, rabbit, skunk, bicycle, plain, trout, wardrobe, bowl, crocodile, tractor, tank, caterpillar, mouse, couch, poppy