paper-with-me

Papers

Identifying Spurious Correlations and Correcting them with an Explanation-based Learning

2022-11-15 · Misgina Tsighe Hagos, Kathleen M. Curran, Brian Mac Namee

Identifying spurious correlations learned by a trained model is at the core of refining a trained model and building a trustworthy model. We present a simple method to identify spurious correlations that have been learned by a model trained for image classification problems. We apply image-level perturbations and monitor changes in certainties of predictions made using the trained model. We demonstrate this approach using an image classification dataset that contains images with synthetically generated spurious regions and show that the trained model was overdependent on spurious regions. Moreover, we remove the learned spurious correlations with an explanation based learning approach.

📄 PDF Abstract BibTeX arXiv:2211.08285

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Language

2022-04-09 · NAACL 2022 7 · Jacob Eisenstein

Spurious correlations are a threat to the trustworthiness of natural language processing systems, motivating research into methods for identifying and eliminating them. However, addressing the problem of spurious correla…

InformativenessVocal Bursts Valence Prediction

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias

2023-05-30 · Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman

Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold…

Inductive Bias

Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions

2026-05-27 · Thomas Vitry, Kieran Edgeworth, Stefan Wermter, Jae Hee Lee arxiv

Vision classifiers can exploit spurious correlations, achieving high in-distribution accuracy yet failing under distribution shift. Existing approaches to bias mitigation and analysis often depend on curated datasets, sp…

Finding and Fixing Spurious Patterns with Explanations

2021-06-03 · Gregory Plumb, Marco Tulio Ribeiro, Ameet Talwalkar

Image classifiers often use spurious patterns, such as "relying on the presence of a person to detect a tennis racket, which do not generalize. In this work, we present an end-to-end pipeline for identifying and mitigati…

Data Augmentation

Uninformative Input Features and Counterfactual Invariance: Two Perspectives on Spurious Correlations in Natural Language

2022-01-16 · ACL ARR January 2022 1 · Anonymous

The natural language processing community has become increasingly interested in spurious correlations, and in methods for identifying and eliminating them. Gardner et al (2021) argue that due to the compositional nature …

counterfactual