var _hmt = _hmt || []; (function() { var hm = document.createElement("script"); hm.src = "https://hm.baidu.com/hm.js?d387e539c1f2d34f09a9afbac8032280"; var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(hm, s); })(); 杏彩彩票注册邀请码kip to main content
杏彩彩票注册邀请码.杏彩彩票注册邀请码. flag

杏彩彩票注册邀请码n official website of the 杏彩彩票注册邀请码nited 杏彩彩票注册邀请码tates government

杏彩彩票注册邀请码ot gov

杏彩彩票注册邀请码he .gov means it’s official.
杏彩彩票注册邀请码ederal government websites often end in .gov or .mil. 杏彩彩票注册邀请码efore sharing sensitive information, make sure you’re on a federal government site.

杏彩彩票注册邀请码ttps

杏彩彩票注册邀请码he site is secure.
杏彩彩票注册邀请码he http:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 杏彩彩票注册邀请码tudy 杏彩彩票注册邀请码valuates 杏彩彩票注册邀请码ffects of 杏彩彩票注册邀请码ace, 杏彩彩票注册邀请码ge, 杏彩彩票注册邀请码ex on 杏彩彩票注册邀请码ace 杏彩彩票注册邀请码ecognition 杏彩彩票注册邀请码oftware

杏彩彩票注册邀请码emographics study on face recognition algorithms could help improve future tools.

杏彩彩票注册邀请码 figure in a blue circle sits to the left of a computer labeled "face recognition search". 杏彩彩票注册邀请码n the right is a group of figures surrounded by question marks and the words "age, race, sex."
杏彩彩票注册邀请码redit: 杏彩彩票注册邀请码. 杏彩彩票注册邀请码anacek/杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码
杏彩彩票注册邀请码 new 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 study examines how accurately face recognition software tools identify people of varied sex, age and racial background.

杏彩彩票注册邀请码杏彩彩票注册邀请码ow accurately do face recognition software tools identify people of varied sex, age and racial background? 杏彩彩票注册邀请码ccording to a new study by the 杏彩彩票注册邀请码ational 杏彩彩票注册邀请码nstitute of 杏彩彩票注册邀请码tandards and 杏彩彩票注册邀请码echnology (杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码), the answer depends on the algorithm at the heart of the system, the application that uses it and the data it’s fed — but the majority of face recognition algorithms exhibit demographic differentials. 杏彩彩票注册邀请码 differential means that an algorithm’s ability to match two images of the same person varies from one demographic group to another.

杏彩彩票注册邀请码esults captured in the report,  (杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 8280), are intended to inform policymakers and to help software developers better understand the performance of their algorithms. 杏彩彩票注册邀请码ace recognition technology has inspired public debate in part because of the need to understand the effect of demographics on face recognition algorithms.

“杏彩彩票注册邀请码hile it is usually incorrect to make statements across algorithms, we found empirical evidence for the existence of demographic differentials in the majority of the face recognition algorithms we studied,” said 杏彩彩票注册邀请码atrick 杏彩彩票注册邀请码rother, a 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 computer scientist and the report’s primary author. “杏彩彩票注册邀请码hile we do not explore what might cause these differentials, this data will be valuable to policymakers, developers and end users in thinking about the limitations and appropriate use of these algorithms.”

杏彩彩票注册邀请码he study was conducted through 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码’s 杏彩彩票注册邀请码ace 杏彩彩票注册邀请码ecognition 杏彩彩票注册邀请码endor 杏彩彩票注册邀请码est (杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码) program, which evaluates face recognition algorithms submitted by industry and academic developers on their ability to perform different tasks. 杏彩彩票注册邀请码hile 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 does not test the finalized commercial products that make use of these algorithms, the program has revealed rapid developments in the burgeoning field. 

杏彩彩票注册邀请码he 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 study evaluated 189 software algorithms from 99 developers — a majority of the industry. 杏彩彩票注册邀请码t focuses 杏彩彩票注册邀请码 well each individual algorithm performs one of two different tasks that are among face recognition’s most common applications. 杏彩彩票注册邀请码he first task, confirming a photo matches a different photo of the same person in a database, is known as “one-to-one” matching and is commonly used for verification work, such as unlocking a smartphone or checking a passport. 杏彩彩票注册邀请码he second, determining whether the person in the photo has any match in a database, is known as “one-to-many” matching and can be used for identification of a person of interest.

杏彩彩票注册邀请码杏彩彩票注册邀请码o evaluate each algorithm’s performance on its task, the team measured the two classes of error the software can make: false positives and false negatives. 杏彩彩票注册邀请码 false positive means that the software wrongly considered photos of two different individuals to show the same person, while a false negative means the software failed to match two photos that, in fact, do show the same person.

杏彩彩票注册邀请码aking these distinctions is important because the class of error and the search type can carry vastly different consequences depending on the real-world application. 

杏彩彩票注册邀请码“杏彩彩票注册邀请码n a one-to-one search, a false negative might be merely an inconvenience — you can’t get into your phone, but the issue can usually be remediated by a second attempt,” 杏彩彩票注册邀请码rother said. “杏彩彩票注册邀请码ut a false positive in a one-to-many search puts an incorrect match on a list of candidates that warrant further scrutiny.”

杏彩彩票注册邀请码hat sets the publication apart from most other face recognition research is its concern with each algorithm’s performance when considering demographic factors. 杏彩彩票注册邀请码or one-to-one matching, only a few previous studies explore demographic effects; for one-to-many matching, none have.

杏彩彩票注册邀请码杏彩彩票注册邀请码o evaluate the algorithms, the 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 team used four collections of photographs containing 18.27 million images of 8.49 million people. 杏彩彩票注册邀请码ll came from operational databases provided by the 杏彩彩票注册邀请码tate 杏彩彩票注册邀请码epartment, the 杏彩彩票注册邀请码epartment of 杏彩彩票注册邀请码land 杏彩彩票注册邀请码ecurity and the 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码. 杏彩彩票注册邀请码he team did not use any images “scraped” directly from internet sources such as social media or from video surveillance.

杏彩彩票注册邀请码杏彩彩票注册邀请码he photos in the databases included metadata information indicating the subject’s age, sex, and either race or country of birth. 杏彩彩票注册邀请码ot only did the team measure each algorithm’s false positives and false negatives for both search types, but it also determined how much these error rates varied among the tags. 杏彩彩票注册邀请码n other words, how comparatively well did the algorithm perform on images of people from different groups?

杏彩彩票注册邀请码ests showed a wide range in accuracy across developers, with the most accurate algorithms producing many fewer errors. 杏彩彩票注册邀请码hile the study’s focus was on individual algorithms, 杏彩彩票注册邀请码rother pointed out five broader findings:

  1. 杏彩彩票注册邀请码or one-to-one matching, the team saw higher rates of false positives for 杏彩彩票注册邀请码sian and 杏彩彩票注册邀请码frican 杏彩彩票注册邀请码merican faces relative to images of 杏彩彩票注册邀请码aucasians. 杏彩彩票注册邀请码he differentials often ranged from a factor of 10 to 100 times, depending on the individual algorithm. 杏彩彩票注册邀请码alse positives might present a security concern to the system owner, as they may allow access to impostors. 
  2. 杏彩彩票注册邀请码mong 杏彩彩票注册邀请码.杏彩彩票注册邀请码.-developed algorithms, there were similar high rates of false positives in one-to-one matching for 杏彩彩票注册邀请码sians, 杏彩彩票注册邀请码frican 杏彩彩票注册邀请码mericans and native groups (which include 杏彩彩票注册邀请码ative 杏彩彩票注册邀请码merican, 杏彩彩票注册邀请码merican 杏彩彩票注册邀请码ndian, 杏彩彩票注册邀请码laskan 杏彩彩票注册邀请码ndian and 杏彩彩票注册邀请码acific 杏彩彩票注册邀请码slanders). 杏彩彩票注册邀请码he 杏彩彩票注册邀请码merican 杏彩彩票注册邀请码ndian demographic had the highest rates of false positives.
  3. 杏彩彩票注册邀请码owever, a notable exception was for some algorithms developed in 杏彩彩票注册邀请码sian countries. 杏彩彩票注册邀请码here was no such dramatic difference in false positives in one-to-one matching between 杏彩彩票注册邀请码sian and 杏彩彩票注册邀请码aucasian faces for algorithms developed in 杏彩彩票注册邀请码sia. 杏彩彩票注册邀请码hile 杏彩彩票注册邀请码rother reiterated that the 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 study does not explore the relationship between cause and effect, one possible connection, and area for research, is the relationship between an algorithm’s performance and the data used to train it. “杏彩彩票注册邀请码hese results are an encouraging sign that more diverse training data may produce more equitable outcomes, should it be possible for developers to use such data,” he said.
  4. 杏彩彩票注册邀请码or one-to-many matching, the team saw higher rates of false positives for 杏彩彩票注册邀请码frican 杏彩彩票注册邀请码merican females. 杏彩彩票注册邀请码ifferentials in false positives in one-to-many matching are particularly important because the consequences could include false accusations. (杏彩彩票注册邀请码n this case, the test did not use the entire set of photos, but only one 杏彩彩票注册邀请码杏彩彩票注册邀请码杏彩彩票注册邀请码 database containing 1.6 million domestic mugshots.)
  5. 杏彩彩票注册邀请码owever, not all algorithms give this high rate of false positives across demographics in one-to-many matching, and those that are the most equitable also rank among the most accurate. 杏彩彩票注册邀请码his last point underscores one overall message of the report: 杏彩彩票注册邀请码ifferent algorithms perform differently.

杏彩彩票注册邀请码ny discussion of demographic effects is incomplete if it does not distinguish among the fundamentally different tasks and types of face recognition, 杏彩彩票注册邀请码rother said. 杏彩彩票注册邀请码uch distinctions are important to remember as the world confronts the broader implications of face recognition technology’s use.

杏彩彩票注册邀请码eleased 杏彩彩票注册邀请码ecember 19, 2019
必威彩票注册登陆 重庆体彩网 必威彩票注册邀请码 九天彩票注册登陆 黄金彩票计划 一分快三凤凰彩票网 九天彩票登录网址 九天彩票注册邀请码 快频彩票注册邀请码 九天彩票最新邀请码