BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers

• URL: http://arxiv.org/abs/2605.28450v1
• Date: Wed, 27 May 2026 13:17:58 GMT
• Title: BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers
• Abstract summary: We introduce BiasEdit, a framework that automatically detects bias attributes from the original dataset and edits them to construct a debiased dataset.<n>Our method operates without manual annotations and can leverage off-the-shelf vision-induced and editing models.
• Score: 13.838654196169612
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the raw Web data often contain spurious correlations and social biases, and neural networks are known for their tendency to learn biases present in data. This can reinforce unfairness in web services and the web data, leading to a vicious cycle. In the context of image classification, networks learn bias attributes for a specific class when a majority of images contain the same attribute only for a given class. Hence, training a fair and debiased classifier from a biased dataset demands handling an imbalanced problem between a majority of images with bias attributes (bias-aligned samples) and a minority without (bias-conflict samples). In this work, we introduce BiasEdit, a modular framework that automatically detects bias attributes from the original dataset and edits them to construct a debiased dataset. Specifically, BiasEdit first detects unknown bias attributes via statistical dependence and mutual information analysis of visual-linguistic representations, and then explicitly edits those attributes using text-guided image editing to generate realistic bias-conflict samples. Unlike prior works that assume known bias attributes or relies on synthetic mixing, our method operates without manual annotations and can leverage off-the-shelf vision-language and editing models. BiasEdit addresses a fundamental challenge in Web-sourced visual AI, mitigating dataset-induced bias and achieving state-of-the-art debiasing performance even when training data are fully biased.

Related papers

• BLADE: Bias-Linked Adaptive DEbiasing [2.7352017408152083]
  BLADE is a generative debiasing framework that requires no prior knowledge of bias or bias-conflicting samples.<n>We evaluate BLADE on multiple benchmark datasets and show that it significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-10-05T12:28:54Z)
• Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video [67.24316233946381]
  Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue. We propose the bias-conflict sample synthesis and adversarial removal debias strategy (BSSARD)
  arXiv  Detail & Related papers  (2024-01-15T09:59:43Z)
• Improving Bias Mitigation through Bias Experts in Natural Language Understanding [10.363406065066538]
  We propose a new debiasing framework that introduces binary classifiers between the auxiliary model and the main model. Our proposed strategy improves the bias identification ability of the auxiliary model.
  arXiv  Detail & Related papers  (2023-12-06T16:15:00Z)
• Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond [93.96982273042296]
  Vision-language (VL) understanding tasks evaluate models' comprehension of complex visual scenes through multiple-choice questions. We have identified two dataset biases that models can exploit as shortcuts to resolve various VL tasks correctly without proper understanding. We propose Adversarial Data Synthesis (ADS) to generate synthetic training and debiased evaluation data. We then introduce Intra-sample Counterfactual Training (ICT) to assist models in utilizing the synthesized training data, particularly the counterfactual data, via focusing on intra-sample differentiation.
  arXiv  Detail & Related papers  (2023-10-23T08:09:42Z)
• 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)
• Echoes: Unsupervised Debiasing via Pseudo-bias Labeling in an Echo Chamber [17.034228910493056]
  This paper presents experimental analyses revealing that the existing biased models overfit to bias-conflicting samples in the training data. We propose a straightforward and effective method called Echoes, which trains a biased model and a target model with a different strategy. Our approach achieves superior debiasing results compared to the existing baselines on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-05-06T13:13:18Z)
• 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)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)
• BiaSwap: Removing dataset bias with bias-tailored swapping augmentation [20.149645246997668]
  Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution. This paper proposes a novel bias-tailored augmentation-based approach, BiaSwap, for learning debiased representation without requiring supervision on the bias type.
  arXiv  Detail & Related papers  (2021-08-23T08:35:26Z)
• Learning Debiased Representation via Disentangled Feature Augmentation [19.348340314001756]
  This paper presents an empirical analysis revealing that training with "diverse" bias-conflicting samples is crucial for debiasing. We propose a novel feature-level data augmentation technique in order to synthesize diverse bias-conflicting samples.
  arXiv  Detail & Related papers  (2021-07-03T08:03:25Z)

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.