yilmazff

candidate_training

Reproducible version of the experiments in "Leveraging inductive bias of neural networks for learning without explicit human annotations"

early_stopping_double_descent

Code for reproducing figures and results in the paper ``Early stopping in deep networks: Double descent and how to eliminate it''

imagenet_candidate_training

Training on noisy Flickr labels without annotators for better classification performance in ImageNet classification problem.

recalibrating_conformal_prediction

QTC: Test-time recalibration of conformal predictors under distribution shift based on unlabeled examples

regularization-wise_double_descent

firebase_art

FIREBASE: An automated framework and algorithm for FIgure REtrieval BAsed on SEmantic-information for articles/documents/lecture_notes

yilmazff/firebase_art

FIREBASE: An automated framework and algorithm for FIgure REtrieval BAsed on SEmantic-information for articles/documents/lecture_notes