Focusing Image Generation to Mitigate Spurious Correlations
Instance features in images exhibit spurious correlations with background features, affecting the training process of deep neural classifiers. This leads to insufficient attention to instance features by the classifier, resulting in erroneous classification outcomes. In this paper, we propose a data augmentation method called Spurious Correlations Guided Synthesis (SCGS) that mitigates spurious correlations through image generation model. This approach does not require expensive spurious attribute (group) labels for the training data and can be widely applied to other debiasing methods. Specifically, SCGS first identifies the incorrect attention regions of a pre-trained classifier on the training images, and then uses an image generation model to generate new training data based on these incorrect attended regions. SCGS increases the diversity and scale of the dataset to reduce the impact of spurious correlations on classifiers. Changes in the classifier's attention regions and experimental results on three different domain datasets demonstrate that this method is effective in reducing the classifier's reliance on spurious correlations.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeData AugmentationDiversityImage GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Spuriousness-Aware Meta-Learning for Learning Robust Classifiers
Spurious correlations are brittle associations between certain attributes of inputs and target variables, such as the correlation between an image background and an object class. Deep image classifiers often leverage the…
AttributeLanguage ModellingMeta-LearningDebiasing Counterfactuals In the Presence of Spurious Correlations
Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rat…
counterfactualImage GenerationRaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time. Existing approaches for addressing spu…
image-classificationImage Classificationzero-shot-classificationZero-Shot LearningLess is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery
In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDIALOG curated in our work. The cur rent models indeed suffer from spurious correlations a…
Causal DiscoveryInformativenessResponse GenerationSpurious Correlations in Reference-Free Evaluation of Text Generation
Model-based, reference-free evaluation metrics have been proposed as a fast and cost-effective approach to evaluate Natural Language Generation (NLG) systems. Despite promising recent results, we find evidence that refer…
Abstractive Text SummarizationText GenerationText Summarization