ML researchers assess spurious correlations via four pragmatic frames (relevance, generalizability, human-likeness, harmfulness) rather than a fixed statistical definition.
Goldenfein, J (2019) The Profiling Potential of Computer Vision and the Challenge of Computational Empiricism
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.
citing papers explorer
-
The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
ML researchers assess spurious correlations via four pragmatic frames (relevance, generalizability, human-likeness, harmfulness) rather than a fixed statistical definition.
-
Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.