Tackling Shortcut Learning in Deep Neural Networks: An Iterative
Approach with Interpretable Models

Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models

20 February 2023

Forough Arabshahi

Kayhan Batmanghelich

Papers citing "Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models"

7 / 7 papers shown

Title
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off M. Zarlenga Pietro Barbiero Gabriele Ciravegna G. Marra Francesco Giannini ... F. Precioso S. Melacci Adrian Weller Pietro Lio' M. Jamnik 68 52 0 19 Sep 2022
Post-hoc Concept Bottleneck Models Mert Yuksekgonul Maggie Wang James Y. Zou 133 182 0 31 May 2022
Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities Julia Rosenzweig Joachim Sicking Sebastian Houben Michael Mock Maram Akila AAML 16 3 0 22 Apr 2021
Gradient Matching for Domain Generalization Yuge Shi Jeffrey S. Seely Philip H. S. Torr Siddharth Narayanaswamy Awni Y. Hannun Nicolas Usunier Gabriel Synnaeve OOD 205 246 0 20 Apr 2021
On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectors Adriano Lucieri Muhammad Naseer Bajwa S. Braun M. I. Malik Andreas Dengel Sheraz Ahmed MedIm 152 64 0 05 May 2020
Out-of-Distribution Generalization via Risk Extrapolation (REx) David M. Krueger Ethan Caballero J. Jacobsen Amy Zhang Jonathan Binas Dinghuai Zhang Rémi Le Priol Aaron Courville OOD 215 888 0 02 Mar 2020
Densely Connected Convolutional Networks Gao Huang Zhuang Liu L. V. D. van der Maaten Kilian Q. Weinberger PINN 3DV 244 35,884 0 25 Aug 2016