ProbeX/Model-J__DINO__model_idx_0912

Model-J: DINO Model (model_idx_0912)

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	DINO
Split	train
Base Model	facebook/dino-vitb16
Dataset	CIFAR100 (50 classes)

Training Hyperparameters

Parameter	Value
Learning Rate	0.0005
LR Scheduler	cosine
Epochs	9
Max Train Steps	2997
Batch Size	64
Weight Decay	0.009
Seed	912
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.5246
Val Accuracy	0.4432
Test Accuracy	0.4302

Training Categories

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

sunflower, palm_tree, porcupine, table, lawn_mower, skyscraper, sweet_pepper, maple_tree, mountain, rocket, whale, dolphin, bear, seal, clock, girl, cattle, television, tractor, worm, plain, wolf, cloud, bus, spider, lizard, camel, caterpillar, tulip, cockroach, elephant, apple, snail, leopard, kangaroo, plate, shark, lion, rabbit, pickup_truck, bottle, dinosaur, lobster, keyboard, tank, aquarium_fish, road, cup, beaver, streetcar