Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation

• URL: http://arxiv.org/abs/2412.09160v1
• Date: Thu, 12 Dec 2024 10:46:14 GMT
• Title: Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation
• Authors: Kirill Sirotkin, Marcos Escudero-Viñolo, Pablo Carballeira, Mayug Maniparambil, Catarina Barata, Noel E. O'Connor,
• Abstract summary: We present a localized counterfactual generation method that preserves image context. Our method results in higher visual and semantic fidelity than state-of-the-art alternatives. Models fine-tuned with our counterfactuals demonstrate measurable bias reduction across multiple metrics.
• Score: 17.53599375848065
• License:
• Abstract: Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and background. We present a localized counterfactual generation method that preserves image context by constraining counterfactual modifications to specific attribute-relevant regions through automated masking and guided inpainting. When applied to the Conceptual Captions dataset for creating gender counterfactuals, our method results in higher visual and semantic fidelity than state-of-the-art alternatives, while maintaining the performance of models trained using only real data on non-human-centric tasks. Models fine-tuned with our counterfactuals demonstrate measurable bias reduction across multiple metrics, including a decrease in gender classification disparity and balanced person preference scores, while preserving ImageNet zero-shot performance. The results establish a framework for creating balanced datasets that enable both accurate bias profiling and effective mitigation.

Related papers

• Counterfactual Image Generation for adversarially robust and interpretable Classifiers [1.3859669037499769]
  We propose a unified framework leveraging image-to-image translation Generative Adrial Networks (GANs) to produce counterfactual samples. This is achieved by combining the classifier and discriminator into a single model that attributes real images to their respective classes and flags generated images as "fake" We show how the model exhibits improved robustness to adversarial attacks, and we show how the discriminator's "fakeness" value serves as an uncertainty measure of the predictions.
  arXiv  Detail & Related papers  (2023-10-01T18:50:29Z)
• Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets [52.77024349608834]
  Vision-language models can perpetuate and amplify societal biases learned during pre-training on uncurated image-text pairs from the internet. COCO Captions is the most commonly used dataset for evaluating bias between background context and the gender of people in-situ. We propose a novel dataset debiasing pipeline to augment the COCO dataset with synthetic, gender-balanced contrast sets.
  arXiv  Detail & Related papers  (2023-05-24T17:59:18Z)
• Gender Biases in Automatic Evaluation Metrics for Image Captioning [87.15170977240643]
  We conduct a systematic study of gender biases in model-based evaluation metrics for image captioning tasks. We demonstrate the negative consequences of using these biased metrics, including the inability to differentiate between biased and unbiased generations. We present a simple and effective way to mitigate the metric bias without hurting the correlations with human judgments.
  arXiv  Detail & Related papers  (2023-05-24T04:27:40Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Counterfactual Generation Under Confounding [24.503075567519048]
  A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations. We propose a counterfactual generation method that learns to modify the value of any attribute in an image and generate new images given a set of observed attributes. Our method is computationally efficient, simple to implement, and works well for any number of generative factors and confounding variables.
  arXiv  Detail & Related papers  (2022-10-22T06:39:22Z)
• Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias [10.639605996067534]
  Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better representations and improve accuracy. In COCO, many object categories have a much higher co-occurrence with men compared to women, which can bias a DNN's prediction in favor of men. We introduce a data repair algorithm using the coefficient of variation, which can curate fair and contextually balanced data for a protected class.
  arXiv  Detail & Related papers  (2021-10-20T06:00:03Z)
• Contrastive Learning for Fair Representations [50.95604482330149]
  Trained classification models can unintentionally lead to biased representations and predictions. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. We propose a method for mitigating bias by incorporating contrastive learning, in which instances sharing the same class label are encouraged to have similar representations.
  arXiv  Detail & Related papers  (2021-09-22T10:47:51Z)
• Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models [86.79402670904338]
  We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
  arXiv  Detail & Related papers  (2021-08-14T16:49:05Z)
• Balancing Biases and Preserving Privacy on Balanced Faces in the Wild [50.915684171879036]
  There are demographic biases present in current facial recognition (FR) models. We introduce our Balanced Faces in the Wild dataset to measure these biases across different ethnic and gender subgroups. We find that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results. We propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2021-03-16T15:05:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.