Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding "spurious" or unstable features whose relationship with the label changes across domains. However, unstable features often carry complementary information that could boost performance if used correctly in the test domain. In this work, we show how this can be done without test-domain labels. In particular, we prove that pseudo-labels based on stable features provide sufficient guidance for doing so, provided that stable and unstable features are conditionally independent given the label. Based on this theoretical insight, we propose Stable Feature Boosting (SFB), an algorithm for: (i) learning a predictor that separates stable and conditionally-independent unstable features; and (ii) using the stable-feature predictions to adapt the unstable-feature predictions in the test domain. Theoretically, we prove that SFB can learn an asymptotically-optimal predictor without test-domain labels. Empirically, we demonstrate the effectiveness of SFB on real and synthetic data.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Spuriosity Didn’t Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding "spurious" or unstable features whose re…
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. Instead of requiring costly changes to one's data or model training, our method better utilizes the data …
Domain-Invariant Disentangled Network for Generalizable Object Detection
We address the problem of domain generalizable object detection, which aims to learn a domain-invariant detector from multiple "seen" domains so that it can generalize well to other "unseen" domains. The generalizati…
DisentanglementDomain Generalizationimage-classificationImage Classification+3StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment
Learning robust representations from data often requires scale, which has led to the success of recent zero-shot models such as CLIP. However, the obtained robustness can easily be deteriorated when these models are fine…
zero-shot-classificationZero-Shot LearningSebra: Debiasing Through Self-Guided Bias Ranking
Ranking samples by fine-grained estimates of spuriosity (the degree to which spurious cues are present) has recently been shown to significantly benefit bias mitigation, over the traditional binary biased-\textit{vs}-unb…
Contrastive Learning