ProbeX/Model-J__ResNet__model_idx_0593

Model-J: ResNet Model (model_idx_0593)

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	7e-05
LR Scheduler	cosine_with_restarts
Epochs	4
Max Train Steps	1332
Batch Size	64
Weight Decay	0.03
Seed	593
Random Crop	False
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.8958
Val Accuracy	0.8483
Test Accuracy	0.8446

Training Categories

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

tank, turtle, lion, snail, aquarium_fish, orange, sea, lobster, orchid, leopard, shark, shrew, cockroach, willow_tree, mushroom, forest, poppy, motorcycle, road, mountain, plate, rabbit, pickup_truck, lamp, rocket, camel, tiger, maple_tree, rose, crocodile, house, skyscraper, lawn_mower, television, raccoon, cup, porcupine, plain, train, girl, sweet_pepper, skunk, otter, bee, keyboard, crab, beaver, dolphin, telephone, trout