On the Impact of Spurious Correlation for Out-of-Distribution Detection

Yifei, Ming,; Yin, Hongcheng; Li, Yixuan

doi:10.1609/aaai.v36i9.21244

Cited by 21 publications

(25 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While Ming, Yin, and Li (2022) do not see success in combining nuisance information with domain generalization algorithms over their baseline ERM solution, Table 1 shows that nuisance-aware OOD detection succeeds over nuisanceunaware ERM. On non-SN-OOD inputs, reweighting yields consistent or better output-based detection performance, and reweighting plus joint independence generally yields compa-AUROC ↑ ERM (Ming) Figure 4: On Waterbirds, using the outer patch as nuisance (patch) yields comparable results to utilizing the exact environment label (exact), which requires external information beyond the image.…”

Section: Methodsmentioning

confidence: 94%

“…Waterbirds. Following Ming, Yin, and Li (2022), we use the Waterbirds dataset generation code from Sagawa et al (2020), generating a different dataset for each correlation strength. We give the validation set the same correlation as the training set, rather than balancing it as done in Sagawa et al (2020).…”

Section: Experimental Set Up Datasetsmentioning

confidence: 99%

“…We give the validation set the same correlation as the training set, rather than balancing it as done in Sagawa et al (2020). We use a subset of the land and water images from PlacesBG dataset (Zhou et al 2018) for SN-OOD inputs, also following (Ming, Yin, and Li 2022).…”

Section: Experimental Set Up Datasetsmentioning

confidence: 99%

“…Instead, many detection methods utilize either the outputs or feature representations of a learned classifier, yielding results much better than those of deep generative models on many tasks (Lee et al 2018;Salehi et al 2021) However, classifier-based OOD detection has been shown to struggle when OOD and in-distribution (ID) inputs share the same values of a nuisance variable that is of no inherent interest to the semantic task, e.g. the background of an image (Ming, Yin, and Li 2022). We call such OOD inputs shared-nuisance OOD (SN-OOD) examples.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection

Zhang¹,

Ranganath²

2023

Preprint

View full text Add to dashboard Cite

Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (OOD) detection of image inputs. However, these methods struggle to detect OOD inputs that share nuisance values (e.g. background) with in-distribution inputs. The detection of shared-nuisance out-of-distribution (SN-OOD) inputs is particularly relevant in real-world applications, as anomalies and in-distribution inputs tend to be captured in the same settings during deployment. In this work, we provide a possible explanation for SN-OOD detection failures and propose nuisance-aware OOD detection to address them. Nuisance-aware OOD detection substitutes a classifier trained via Empirical Risk Minimization (ERM) and cross-entropy loss with one that 1. is trained under a distribution where the nuisance-label relationship is broken and 2. yields representations that are independent of the nuisance under this distribution, both marginally and conditioned on the label. We can train a classifier to achieve these objectives using Nuisance-Randomized Distillation (NURD), an algorithm developed for OOD generalization under spurious correlations. Output-and feature-based nuisance-aware OOD detection perform substantially better than their original counterparts, succeeding even when detection based on domain generalization algorithms fails to improve performance.

show abstract

Section: Methodsmentioning

confidence: 94%

Section: Experimental Set Up Datasetsmentioning

confidence: 99%

Section: Experimental Set Up Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection

Zhang¹,

Ranganath²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…It is shown that grouping the labels for in-distribution data can be effective in OOD detection for large semantic space. In(Ming, Yin, and Li 2022), the effect of spurious correlation is studied for OOD detection. Huang, Geng, and Li derived a scoring function termed GradNorm from the gradient space.…”

mentioning

confidence: 99%

Provable Guarantees for Understanding Out-of-Distribution Detection

Morteza

2022

AAAI

Self Cite

View full text Add to dashboard Cite

Out-of-distribution (OOD) detection is important for deploying machine learning models in the real world, where test data from shifted distributions can naturally arise. While a plethora of algorithmic approaches have recently emerged for OOD detection, a critical gap remains in theoretical understanding. In this work, we develop an analytical framework that characterizes and unifies the theoretical understanding for OOD detection. Our analytical framework motivates a novel OOD detection method for neural networks, GEM, which demonstrates both theoretical and empirical superiority. In particular, on CIFAR-100 as in-distribution data, our method outperforms a competitive baseline by 16.57% (FPR95). Lastly, we formally provide provable guarantees and comprehensive analysis of our method, underpinning how various properties of data distribution affect the performance of OOD detection.

show abstract

Weighting non-IID batches for out-of-distribution detection

Zhao,

Cao

2024

Mach Learn

View full text Add to dashboard Cite

A standard network pretrained on in-distribution (ID) samples could make high-confidence predictions on out-of-distribution (OOD) samples, leaving the possibility of failing to distinguish ID and OOD samples in the test phase. To address this over-confidence issue, the existing methods improve the OOD sensitivity from modeling perspectives, i.e., retraining it by modifying training processes or objective functions. In contrast, this paper proposes a simple but effective method, namely Weighted Non-IID Batching (WNB), by adjusting batch weights. WNB builds on a key observation: increasing the batch size can improve the OOD detection performance. This is because a smaller batch size may make its batch samples more likely to be treated as non-IID from the assumed ID, i.e., associated with an OOD. This causes a network to provide high-confidence predictions for all samples from the OOD. Accordingly, WNB applies a weight function to weight each batch according to the discrepancy between batch samples and the entire training ID dataset. Specifically, the weight function is derived by minimizing the generalization error bound. It ensures that the weight function assigns larger weights to batches with smaller discrepancies and makes a trade-off between ID classification and OOD detection performance. Experimental results show that incorporating WNB into state-of-the-art OOD detection methods can further improve their performance.

show abstract

On the Impact of Spurious Correlation for Out-of-Distribution Detection

Cited by 21 publications

References 33 publications

Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection

Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection

Provable Guarantees for Understanding Out-of-Distribution Detection

Weighting non-IID batches for out-of-distribution detection

Contact Info

Product

Resources

About