Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints

@inproceedings{Zhao2017MenAL,
  title={Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints},
  author={Jieyu Zhao and Tianlu Wang and Mark Yatskar and Vicente Ordonez and Kai-Wei Chang},
  booktitle={EMNLP},
  year={2017}
}
Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. [...] Key Method We propose to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for collective inference. Our method results in almost no performance loss for the underlying recognition task but decreases the magnitude of bias amplification by 47.5% and 40.5% for multilabel classification…Expand
Identifying and Reducing Gender Bias in Word-Level Language Models
TLDR
This study proposes a metric to measure gender bias and proposes a regularization loss term for the language model that minimizes the projection of encoder-trained embeddings onto an embedding subspace that encodes gender and finds this regularization method to be effective in reducing gender bias. Expand
Women also Snowboard: Overcoming Bias in Captioning Models
TLDR
A new Equalizer model is introduced that ensures equal gender probability when gender Evidence is occluded in a scene and confident predictions when gender evidence is present and has lower error than prior work when describing images with people and mentioning their gender and more closely matches the ground truth ratio of sentences including women to sentences including men. Expand
Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
  • Jialu Wang, Yang Liu, Xin Eric Wang
  • Computer Science
  • ArXiv
  • 2021
Internet search affects people’s cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good. We study a unique gender bias in image searchExpand
Understanding and Evaluating Racial Biases in Image Captioning
TLDR
Differences in caption performance, sentiment, and word choice between images of lighter versus darker-skinned people are found to be greater in modern captioning systems compared to older ones, thus leading to concerns that without proper consideration and mitigation these differences will only become increasingly prevalent. Expand
A Dataset for Tackling Gender Bias in Text
Gender bias is found in personal conversations, in the media, in historical writings, popular culture, in the labor force, household responsibilities and now in machines (Fiebert and Meyer, 1997;Expand
Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models
TLDR
This work investigates gender bias in the COCO captioning dataset and shows that it engenders not only from the statistical distribution of genders with contexts but also from the flawed annotation by the human annotators. Expand
Predicting Visual Political Bias Using Webly Supervised Data and an Auxiliary Task
  • Christopher Thomas, Adriana Kovashka
  • International Journal of Computer Vision
  • 2021
The news media shape public opinion, and often, the visual bias they contain is evident for careful human observers. This bias can be inferred from how different media sources portray differentExpand
Quantifying Social Biases in Contextual Word Representations
TLDR
A template-based method to quantify bias in BERT is proposed and it is shown that this method obtains more consistent results in capturing social biases than the traditional cosine based method. Expand
To "See" is to Stereotype
TLDR
A controlled experiment is designed, to examine the interdependence between algorithmic recognition of context and the depicted person's gender, and to create a highly controlled dataset of people images, imposed on gender-stereotyped backgrounds. Expand
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
TLDR
A simple but surprisingly effective visual recognition benchmark for studying bias mitigation, and a simple but similarly effective alternative to the inference-time Reducing Bias Amplification method of Zhao et al., and design a domain-independent training technique that outperforms all other methods. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
TLDR
This work empirically demonstrates that its algorithms significantly reduce gender bias in embeddings while preserving the its useful properties such as the ability to cluster related concepts and to solve analogy tasks. Expand
Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels
TLDR
This paper proposes an algorithm to decouple the human reporting bias from the correct visually grounded labels, and shows significant improvements over traditional algorithms for both image classification and image captioning, doubling the performance of existing methods in some cases. Expand
Semantics derived automatically from language corpora necessarily contain human biases
TLDR
It is shown for the first time that human-like semantic biases result from the application of standard machine learning to ordinary language---the same sort of language humans are exposed to every day. Expand
Show and tell: A neural image caption generator
TLDR
This paper presents a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. Expand
Semantics derived automatically from language corpora contain human-like biases
TLDR
It is shown that machines can learn word associations from written texts and that these associations mirror those learned by humans, as measured by the Implicit Association Test (IAT), and that applying machine learning to ordinary human language results in human-like semantic biases. Expand
Commonly Uncommon: Semantic Sparsity in Situation Recognition
TLDR
This paper studies semantic sparsity in situation recognition, the task of producing structured summaries of what is happening in images, including activities, objects and the roles objects play within the activity. Expand
Situation Recognition: Visual Semantic Role Labeling for Image Understanding
This paper introduces situation recognition, the problem of producing a concise summary of the situation an image depicts including: (1) the main activity (e.g., clipping), (2) the participatingExpand
Tractable Semi-supervised Learning of Complex Structured Prediction Models
TLDR
An approximate semi-supervised learning method that uses piecewise training for estimating the model weights and a dual decomposition approach for solving the inference problem of finding the labels of unlabeled data subject to domain specific constraints is proposed. Expand
Constrained Semi-supervised Learning in the Presence of Unanticipated Classes
TLDR
This thesis argues that many AKBC tasks which have previously been addressed separately can be viewed as instances of single abstract problem: multiview semisupervised learning with an incomplete class hierarchy, and presents a generic EM framework for solving this abstract task. Expand
VQA: Visual Question Answering
We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural languageExpand
...
1
2
3
4
5
...