Assessing Intersectional Bias in Representations of Pre-Trained Image Recognition Models

• URL: http://arxiv.org/abs/2506.03664v2
• Date: Fri, 06 Jun 2025 13:29:49 GMT
• Title: Assessing Intersectional Bias in Representations of Pre-Trained Image Recognition Models
• Authors: Valerie Krug, Sebastian Stober,
• Abstract summary: We investigate biases in the representations of commonly used ImageNet classifiers for facial images.<n>We find that representations in ImageNet classifiers particularly allow differentiation between ages.<n>Less strongly pronounced, the models appear to associate certain ethnicities and distinguish genders in middle-aged groups.
• Score: 0.1074267520911262
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Learning models have achieved remarkable success. Training them is often accelerated by building on top of pre-trained models which poses the risk of perpetuating encoded biases. Here, we investigate biases in the representations of commonly used ImageNet classifiers for facial images while considering intersections of sensitive variables age, race and gender. To assess the biases, we use linear classifier probes and visualize activations as topographic maps. We find that representations in ImageNet classifiers particularly allow differentiation between ages. Less strongly pronounced, the models appear to associate certain ethnicities and distinguish genders in middle-aged groups.

Related papers

• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• Classes Are Not Equal: An Empirical Study on Image Recognition Fairness [100.36114135663836]
  We experimentally demonstrate that classes are not equal and the fairness issue is prevalent for image classification models across various datasets. Our findings reveal that models tend to exhibit greater prediction biases for classes that are more challenging to recognize. Data augmentation and representation learning algorithms improve overall performance by promoting fairness to some degree in image classification.
  arXiv  Detail & Related papers  (2024-02-28T07:54:50Z)
• 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)
• DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation [27.780618650580923]
  Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted correlations "data biases," and the visual features causing data biases "bias factors" It is challenging to identify and mitigate biases automatically without human intervention.
  arXiv  Detail & Related papers  (2022-09-14T00:44:41Z)
• Are Commercial Face Detection Models as Biased as Academic Models? [64.71318433419636]
  We compare academic and commercial face detection systems, specifically examining robustness to noise. We find that state-of-the-art academic face detection models exhibit demographic disparities in their noise robustness. We conclude that commercial models are always as biased or more biased than an academic model.
  arXiv  Detail & Related papers  (2022-01-25T02:21:42Z)
• Visual Recognition with Deep Learning from Biased Image Datasets [6.10183951877597]
  We show how biasing models can be applied to remedy problems in the context of visual recognition. Based on the (approximate) knowledge of the biasing mechanisms at work, our approach consists in reweighting the observations. We propose to use a low dimensional image representation, shared across the image databases.
  arXiv  Detail & Related papers  (2021-09-06T10:56:58Z)
• 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)
• Understanding Gender and Racial Disparities in Image Recognition Models [0.0]
  We investigate a multi-label softmax loss with cross-entropy as the loss function instead of a binary cross-entropy on a multi-label classification problem. We use the MR2 dataset to evaluate the fairness in the model outcomes and try to interpret the mistakes by looking at model activations and suggest possible fixes.
  arXiv  Detail & Related papers  (2021-07-20T01:05:31Z)
• Age and Gender Prediction From Face Images Using Attentional Convolutional Network [6.3344832182228]
  We propose a deep learning framework, based on the ensemble of attentional and residual convolutional networks, to predict gender and age group of facial images with high accuracy rate. Our model is trained on a popular face age and gender dataset, and achieved promising results.
  arXiv  Detail & Related papers  (2020-10-08T06:33:55Z)
• InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics [73.85525896663371]
  This work explores the biases in learning processes based on deep neural network architectures. We employ two gender detection models based on popular deep neural networks. We propose InsideBias, a novel method to detect biased models.
  arXiv  Detail & Related papers  (2020-04-14T15:20:50Z)

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.