Catch up on the latest AI articles

Visual Chirality, Which You May Want To Understand In Terms Of The Data Augmentation Technique, Is

Visual Chirality, Which You May Want To Understand In Terms Of The Data Augmentation Technique, Is

Deep Learning

3 main points
✔️ Proposes a new concept in data augmentation
✔️ Recognizes left-right reversals that have not been noticed by humans

✔️ Extensions based on this property can be expected to further improve accuracy

Visual Chirality
written by Zhiqiu LinJin SunAbe DavisNoah Snavely
(Submitted on 16 Jun 2020)

Comments: Published by CVPR2020
Subjects: Computer Vision and Pattern Recognition (cs.CV)


Data augmentation by left-right flipping is a very common method of data augmentation, and some of you may have used it without paying attention to it. I had been using it pretty much as a matter of course until I read this paper. The authors recognized the principle and the kind of change caused by the left-right flipping of images, but it was not clear what kind of change the left-right flipping caused in the statistical data of the images. I think you can imagine the image. I think many people also think that the statistics of the image will be flipped left and right. The authors easily answer those questions with their We propose a method for quantifying visual chirality. First of all. We'll look at what Visual Chirality is.

To read more,

Please register with AI-SCHOLAR.

Sign up for free in 1 minute

運営 avatar
AI-SCHOLAR is a commentary media that introduces the latest articles on AI (artificial intelligence) in an easy-to-understand manner. The role of AI is not limited to technological innovation, as Japan's scientific capabilities are declining and the government continues to cut back on research budgets. Communicating with the world the technology of AI, its applications, and the context of the basic science that supports it is an important outreach, and can greatly influence society's understanding and impression of science. AI-SCHOLAR is designed to help eliminate the gaps in understanding of AI between the general public and experts, and to contribute to the integration of AI into society. In addition, we would like to help you embody your learning and research experiences in the media and express them in society. Anyone can explain advanced and difficult matters in difficult terms, but AI-SCHOLAR pursues "readability” and "comprehensibility" by making full use of vocabulary and design in conveying information as a medium.

If you have any suggestions for improvement of the content of the article,
please contact the AI-SCHOLAR editorial team through the contact form.

Contact Us