Matched sample selection with GANs for mitigating attribute confounding

• URL: http://arxiv.org/abs/2103.13455v1
• Date: Wed, 24 Mar 2021 19:18:44 GMT
• Title: Matched sample selection with GANs for mitigating attribute confounding
• Authors: Chandan Singh, Guha Balakrishnan, Pietro Perona
• Abstract summary: We propose a matching approach that selects a subset of images from the full dataset with balanced attribute distributions across protected attributes. Our matching approach first projects real images onto a generative network's latent space in a manner that preserves semantic attributes. It then finds adversarial matches in this latent space across a chosen protected attribute, yielding a dataset where semantic and perceptual attributes are balanced across the protected attribute.
• Score: 30.488267816304177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society. However, significant correlations between attributes in benchmark datasets make it difficult to separate algorithmic bias from dataset bias. To mitigate such attribute confounding during bias analysis, we propose a matching approach that selects a subset of images from the full dataset with balanced attribute distributions across protected attributes. Our matching approach first projects real images onto a generative adversarial network (GAN)'s latent space in a manner that preserves semantic attributes. It then finds image matches in this latent space across a chosen protected attribute, yielding a dataset where semantic and perceptual attributes are balanced across the protected attribute. We validate projection and matching strategies with qualitative, quantitative, and human annotation experiments. We demonstrate our work in the context of gender bias in multiple open-source facial-recognition classifiers and find that bias persists after removing key confounders via matching. Code and documentation to reproduce the results here and apply the methods to new data is available at https://github.com/csinva/matching-with-gans .

Related papers

• AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation [53.65701943405546]
  We learn adaptive inclusive tokens to shift the attribute distribution of the final generative outputs. Our method requires neither explicit attribute specification nor prior knowledge of the bias distribution. Our method achieves comparable performance to models that require specific attributes or editing directions for generation.
  arXiv  Detail & Related papers  (2024-06-18T17:22:23Z)
• Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair [36.221761997349795]
  Deep neural networks rely on bias attributes that are spuriously correlated with a target class in the presence of dataset bias. This paper proposes a method that provides the model with explicit spatial guidance that indicates the region of intrinsic features. Experiments demonstrate that our method achieves state-of-the-art performance on synthetic and real-world datasets with various levels of bias severity.
  arXiv  Detail & Related papers  (2024-04-30T04:13:14Z)
• Leveraging vision-language models for fair facial attribute classification [19.93324644519412]
  General-purpose vision-language model (VLM) is a rich knowledge source for common sensitive attributes. We analyze the correspondence between VLM predicted and human defined sensitive attribute distribution. Experiments on multiple benchmark facial attribute classification datasets show fairness gains of the model over existing unsupervised baselines.
  arXiv  Detail & Related papers  (2024-03-15T18:37:15Z)
• Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval [65.43522019468976]
  We propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes. We develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors. Our models are equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities.
  arXiv  Detail & Related papers  (2023-11-21T08:20:38Z)
• Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning [52.506434446439776]
  Compositional zero-shot learning (CZSL) aims to recognize compositions with prior knowledge of known primitives (attribute and object) We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL.
  arXiv  Detail & Related papers  (2023-08-08T03:24:21Z)
• Fairness via Adversarial Attribute Neighbourhood Robust Learning [49.93775302674591]
  We propose a principled underlineRobust underlineAdversarial underlineAttribute underlineNeighbourhood (RAAN) loss to debias the classification head.
  arXiv  Detail & Related papers  (2022-10-12T23:39:28Z)
• CAT: Controllable Attribute Translation for Fair Facial Attribute Classification [14.191129493685212]
  In facial attribute classification, dataset bias stems from both protected attribute level and facial attribute level. We propose an effective pipeline to generate high-quality and sufficient facial images with desired facial attributes. Our method outperforms both resampling and balanced dataset construction to address dataset bias.
  arXiv  Detail & Related papers  (2022-09-14T18:04:20Z)
• Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition [50.932864767867365]
  We propose a framework that consists of two complementary regularizations to achieve spatial and semantic consistency for each attribute. Based on the precise attribute locations, we propose a semantic consistency regularization to extract intrinsic and discriminative semantic features. Results show that the proposed method performs favorably against state-of-the-art methods without increasing parameters.
  arXiv  Detail & Related papers  (2021-09-13T03:36:44Z)
• Fair Attribute Classification through Latent Space De-biasing [17.647146032798005]
  We introduce a method for training accurate target classifiers while mitigating biases that stem from correlations. We use GANs to generate realistic-looking images, and perturb these images in the underlying latent space to generate training data that is balanced for each protected attribute. We conduct a thorough evaluation across multiple target labels and protected attributes in the CelebA dataset, and provide an in-depth analysis and comparison to existing literature in the space.
  arXiv  Detail & Related papers  (2020-12-02T19:18:58Z)
• Not All Datasets Are Born Equal: On Heterogeneous Data and Adversarial Examples [46.625818815798254]
  We argue that machine learning models trained on heterogeneous data are as susceptible to adversarial manipulations as those trained on homogeneous data. We introduce a generic optimization framework for identifying adversarial perturbations in heterogeneous input spaces. Our results demonstrate that despite the constraints imposed on input validity in heterogeneous datasets, machine learning models trained using such data are still equally susceptible to adversarial examples.
  arXiv  Detail & Related papers  (2020-10-07T05:24:23Z)
• Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition [102.45926816660665]
  We propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples. The principle lies in that attribute features are shared among fine-grained sub-categories, and can be seamlessly transferred among images.
  arXiv  Detail & Related papers  (2020-04-06T14:06:47Z)

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.