Pith. sign in

REVIEW 1 cited by

Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.03649 v1 pith:5NSFWQE6 submitted 2024-05-06 cs.LG cs.CV

classification cs.LGcs.CV
keywords spuriouscorrelationstrainingclassifierclassifierscorrelationattributesautomatically
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious correlations typically relies on annotations of spurious correlations in data, which are often expensive to get. In this paper, we tackle an annotation-free setting and propose a self-guided spurious correlation mitigation framework. Our framework automatically constructs fine-grained training labels tailored for a classifier obtained with empirical risk minimization to improve its robustness against spurious correlations. The fine-grained training labels are formulated with different prediction behaviors of the classifier identified in a novel spuriousness embedding space. We construct the space with automatically detected conceptual attributes and a novel spuriousness metric which measures how likely a class-attribute correlation is exploited for predictions. We demonstrate that training the classifier to distinguish different prediction behaviors reduces its reliance on spurious correlations without knowing them a priori and outperforms prior methods on five real-world datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Improving Group Robustness on Spurious Correlation via Evidential Alignment

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Evidential Alignment improves worst-group accuracy by upweighting a biased model's high-uncertainty errors and retraining the last layer with a calibration set, without group annotations.

Pith tools