ProbeX/Model-J__ResNet__model_idx_0004

Model-J: ResNet Model (model_idx_0004)

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	cosine_with_restarts
Epochs	5
Max Train Steps	1665
Batch Size	64
Weight Decay	0.007
Seed	4
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.8256
Val Accuracy	0.8125
Test Accuracy	0.8008

Training Categories

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

palm_tree, rabbit, caterpillar, camel, plate, table, cattle, skyscraper, snake, sweet_pepper, forest, willow_tree, couch, squirrel, cockroach, clock, bear, bottle, shark, rocket, house, skunk, lion, poppy, sunflower, turtle, orange, wolf, dolphin, telephone, bridge, cloud, castle, whale, lobster, wardrobe, crab, trout, mushroom, lizard, lamp, woman, mountain, pear, bee, pine_tree, tiger, aquarium_fish, ray, chimpanzee