paper-with-me

Papers

Focusing Image Generation to Mitigate Spurious Correlations

2024-12-27 · XueWei Li, Zhenzhen Nie, Mei Yu, Zijian Zhang, Jie Gao, Tianyi Xu, Zhiqiang Liu

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.

📄 PDF Abstract BibTeX arXiv:2412.19457

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeData AugmentationDiversityImage Generation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Spuriousness-Aware Meta-Learning for Learning Robust Classifiers

2024-06-15 · Guangtao Zheng, Wenqian Ye, Aidong Zhang

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-Learning

Debiasing Counterfactuals In the Presence of Spurious Correlations

2023-08-21 · Amar Kumar, Nima Fathi, Raghav Mehta, Brennan Nichyporuk 외

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 Generation

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

2024-11-06 · Maya Varma, Jean-Benoit Delbrouck, Zhihong Chen, Akshay Chaudhari 외

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 Learning

Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery

2023-03-02 · Tao Feng, Lizhen Qu, Gholamreza Haffari

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 Generation

Spurious Correlations in Reference-Free Evaluation of Text Generation

2022-04-21 · ACL 2022 5 · Esin Durmus, Faisal Ladhak, Tatsunori Hashimoto

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