Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success

16 August 2022

Papers citing "Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success"

6 / 6 papers shown

Title
End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection Jaemin Yoo Lingxiao Zhao L. Akoglu 30 4 0 21 Jun 2023
Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images Philipp Liznerski Lukas Ruff Robert A. Vandermeulen Billy Joe Franks Klaus-Robert Muller Marius Kloft UQCV 45 44 0 23 May 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 305 7,434 0 11 Nov 2021
Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection Marco Rudolph Tom Wehrbein Bodo Rosenhahn Bastian Wandt UQCV 78 208 0 06 Oct 2021
Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges B. Bischl Martin Binder Michel Lang Tobias Pielok Jakob Richter ... Theresa Ullmann Marc Becker A. Boulesteix Difan Deng Marius Lindauer 79 448 0 13 Jul 2021
Zero-Shot Text-to-Image Generation Aditya A. Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen Ilya Sutskever VLM 255 4,777 0 24 Feb 2021