There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

비만아 부모의 돌봄 경험: q 방법론

One of the critical steps in biometrics pipeline is detection of presentation attacks, a physical adversary. Several presentation (adversary) attack detection (PAD) algorithms, including iris PAD, have been proposed and have shown superlative performance. However, a recent study, on a small-scale database, has highlighted that iris PAD may have gender biases. In this research, we present a rigorous study on gender bias in iris presentation attack detection algorithms using a large-scale and gender-balanced database. The paper provides several interesting observations which can help in building future presentation attack detection algorithms with aim of fair treatment of each demography. In addition, we also present a robust iris presentation attack detection algorithm by combining gender-covariate based classifiers. The proposed robust classifier not only reduces the difference in accuracy between different genders but also improves the overall performance of the PAD system.

Misclassifications of Contact Lens Iris PAD Algorithms: Is it Gender Bias or Environmental Conditions?

Uniform Misclassification Loss for Unbiased Model Prediction

Chikankari is an ancient and traditional embroidery technique that originated in Lucknow, a city in north-eastern India. The artisans of Chikan embroidery are outspread in Lucknow and nearby villages of Sitapur district. The rural people of Sitapur villages are largely dependent on the Chikankari embroidery for their livelihood and the embroidery is very popular among rural ladies. Socio-economic status of a person is the economic and social position of the person based on education, income and occupation in relation to others. It was found in the study that age group 20-40 were dominating in Chikankari work as they faces low health problems as compared to higher age group. Modified Kuppuswamy Socio-economic scale updated for the year 2019, was used to calculate the socio-economic status of the respondents. Socio-economic status of the worker shows that they were mostly upper lower class (60%) and lower middle class (40%). Nearly all subjects (99%) had income below 5000/month and the average income from Chikankari is rupees 2566.66/month/person, while the income of the family/household income mostly range between rupees 19516-29199/month and the average income was rupees 20542.91/month. Most of the Chikankari workers had kuchha houses and uses wood for cooking on traditional chulha. Public hand pumps were the source to drink water. They had very small or no land holding and daily wages are the source of income to fulfill their daily needs.

/pdf/socio-economic-status-of-female-workers-engaged-in-2ig2g8tw.pdf

Socio-economic Status of Female Workers Engaged in Traditional Chikankari under Sitapur District

Recent studies have highlighted a major caveat in several popular deep learning based face recognition algorithms. Despite their high accuracy, they have shown to exhibit biased behavior by achieving sub-par performance on images belonging to different sub-groups. Such behavior can often lead to unfair predictions, thus presenting a need to develop fairer models with unprejudiced behavior. This research proposes Detox loss, a novel bias invariant feature learning loss function for learning unbiased models. The proposed loss can be used to: (i) learn fairer deep learning classifiers, and (ii) mitigate bias from existing pre-trained networks, especially in the challenging constraint of imbalanced training data with respect to a protected attribute. Conceptually, the Detox loss enforces that the learned features are distinguished based on the task label only, while eliminating any distinction based on the biasing-attribute. This is achieved by incorporating three fairness constraints while training with the traditional classification loss: (i) proposed Exclusion loss, (ii) proposed Inclusion loss, and (iii) proposed Feature-distillation loss. The efficacy of the Detox loss is demonstrated on two facial analysis tasks: (i) age-group prediction and (ii) gender prediction, under the protected attribute of ethnicity for learning fairer models and de-biasing existing models, with varying imbalanced training data distributions. Across two different protocols, three setups, and two tasks, the Detox loss obtains state of the art performance without the need of multi-labeled training data. For example, on the challenging Pilot Parliaments Benchmark (PPB) dataset, the Detox loss obtains a balanced accuracy and $F_{1}$ score of 96.1% and 96.6%, as compared to the state-of-the-art performance of 94.1% and 93.6%, respectively.

Richa Singh

Papers

Misclassifications of Contact Lens Iris PAD Algorithms: Is it Gender Bias or Environmental Conditions?

Uniform Misclassification Loss for Unbiased Model Prediction

Socio-economic Status of Female Workers Engaged in Traditional Chikankari under Sitapur District

Detox Loss: Fairness Constraints for Learning With Imbalanced Data

Semi-supervised learning via triplet network based active learning