ProbeX/Model-J__ResNet__model_idx_0486

Model-J: ResNet Model (model_idx_0486)

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	linear
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.009
Seed	486
Random Crop	False
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9329
Val Accuracy	0.8627
Test Accuracy	0.8646

Training Categories

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

telephone, worm, crocodile, house, beetle, tank, cockroach, couch, lamp, tractor, bed, bee, wardrobe, cloud, sunflower, aquarium_fish, cup, flatfish, bear, shrew, porcupine, mushroom, ray, mouse, hamster, apple, lawn_mower, dolphin, cattle, poppy, baby, snake, leopard, rabbit, shark, oak_tree, skunk, table, crab, seal, orange, boy, lizard, castle, otter, bottle, rocket, maple_tree, bowl, rose