paper-with-me

Papers

Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation

2023-10-02 · Sidney Bender, Christopher J. Anders, Pattarawatt Chormai, Heike Marxfeld, Jan Herrmann, Grégoire Montavon

This paper introduces a novel technique called counterfactual knowledge distillation (CFKD) to detect and remove reliance on confounders in deep learning models with the help of human expert feedback. Confounders are spurious features that models tend to rely on, which can result in unexpected errors in regulated or safety-critical domains. The paper highlights the benefit of CFKD in such domains and shows some advantages of counterfactual explanations over other types of explanations. We propose an experiment scheme to quantitatively evaluate the success of CFKD and different teachers that can give feedback to the model. We also introduce a new metric that is better correlated with true test performance than validation accuracy. The paper demonstrates the effectiveness of CFKD on synthetically augmented datasets and on real-world histopathological datasets.

📄 PDF Abstract BibTeX arXiv:2310.01011

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples

2025-10-20 · Sidney Bender, Ole Delzer, Jan Herrmann, Heike Antje Marxfeld 외 arxiv

Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-supervised models. Group distributional robus…

Knowledge Distillation

Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks

2023-04-12 · Lorenz Linhardt, Klaus-Robert Müller, Grégoire Montavon

Robustness has become an important consideration in deep learning. With the help of explainable AI, mismatches between an explained model's decision strategy and the user's domain knowledge (e.g. Clever Hans effects) hav…

The Clever Hans Effect in Anomaly Detection

2020-06-18 · Jacob Kauffmann, Lukas Ruff, Grégoire Montavon, Klaus-Robert Müller

The 'Clever Hans' effect occurs when the learned model produces correct predictions based on the 'wrong' features. This effect which undermines the generalization capability of an ML model and goes undetected by standard…

Anomaly DetectionExplainable Artificial Intelligence (XAI)Outlier Detection

Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Models

2026-01-29 · Sidney Bender, Marco Morik arxiv

Foundation models, despite their robust zero-shot capabilities, remain vulnerable to spurious correlations and 'Clever Hans' strategies. Existing mitigation methods often rely on unavailable group labels or computational…

Knowledge Distillation

Imbalanced Classification through the Lens of Spurious Correlations

2025-10-31 · Jakob Hackstein, Sidney Bender arxiv

Class imbalance poses a fundamental challenge in machine learning, frequently leading to unreliable classification performance. While prior methods focus on data- or loss-reweighting schemes, we view imbalance as a data …