cs.CVNov 17, 2026

Let Samples Sing in Chorus: Mitigating Spurious Correlations via Cross-view Consensus

Authors: Weiwei Li, Junzhuo Liu, Tong Chu, Hengfu Yu, Yinjie Lei, Wen Li

Organizations: University of Electronic Science and Technology of China · Sichuan University

Abstract

Deep models often rely on spurious correlations that fail on underrepresented groups. Existing methods either correct human-specified bias attributes or infer unknown biases from the learned representation space. However, annotated attributes may differ from the shortcuts actually used by a model, while a single representation provides incomplete and potentially noisy evidence. Our key insight is that a bias obscured in one feature space may be clearer in another. In this work, we propose CHORD (Cross-view Harmonic Outlier Reversal for Debiasing), a multi-view framework that allows samples to "sing in chorus" across diverse representation spaces to achieve robust cross-view consensus. CHORD aggregates aggregates within-class partitions in each view, which is a proxy for specifying candidate biases, to debias the target representation and classifier without bias supervision. Experiments on seven benchmarks across vision, language, speech, and medical imaging show consistent improvements in worst-group accuracy. Code and checkpoints are available at https://github.com/davelee-uestc/chord_debiasing_public .

Figures & tables

Explore similar work

CardsList
  1. Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement

    Jun 23, 2026Xiangqian Zhao, Xinyang Jiang, Zhipeng Xu +5Disentangled Representation LearningDebiased ML

  2. Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing

    Jun 1, 2026Arda Fazla, Abolfazl HashemiDebiased MLTraining Data Selection

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

    May 27, 2026Thomas Vitry, Kieran Edgeworth, Stefan Wermter +1Debiased MLSpurious Correlation Robustness