ProbeX/Model-J__ResNet__model_idx_0423

Model-J: ResNet Model (model_idx_0423)

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	0.0005
LR Scheduler	constant
Epochs	6
Max Train Steps	1998
Batch Size	64
Weight Decay	0.005
Seed	423
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.9540
Val Accuracy	0.8632
Test Accuracy	0.8638

Training Categories

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

pear, rabbit, crocodile, porcupine, trout, wolf, apple, pine_tree, snail, bear, shark, cloud, worm, bowl, couch, lamp, clock, mountain, dinosaur, baby, aquarium_fish, television, fox, maple_tree, rose, bicycle, pickup_truck, spider, tiger, shrew, telephone, streetcar, sea, boy, man, bridge, woman, skyscraper, keyboard, hamster, skunk, orchid, whale, cattle, oak_tree, bed, bus, possum, leopard, orange