9th CODH Seminar
Computer Vision with Limited Labeled Data

We are pleased to announce that Satoshi Tsutsui, a PhD candidate at Indiana University in USA, will give a talk about computer vision, especially about computer vision with limited labeled data. You are all invited. Registration in advance is required. #codh9

Basic Information

Title Computer Vision with Limited Labeled Data
Speaker Satoshi Tsutsui
Date 16:30-17:30, January 8 (Tue), 2019
Venue 1208 Meeting Room (12F), National Institute of Informatics. Access to NII.
Language English
Abstract Computer vision is making remarkable progress these days supported by deep learning. Deep leaning requires huge amount of training data, but the cost to annotate many images is often high. Various approaches have been proposed to circumvent this problem such as transfer learning, semi-supervised learning, data argumentation, and training data synthesis, but the best strategy depends on the specific application. This talk discusses several case studies on computer vision with limited labeled data. The examples include scientific figure detection, drivable space segmentation for self-driving cars, anatomical segmentation for pelvic magnetic resonance images, nail detection for nail disease images, and children's visual learning analysis with head-mounted camera.
Bio Satoshi Tsutsui is a PhD candidate at Indiana University in USA, advised by David Crandall. He is interested in computer vision, deep learning, and their applications. In the past, he interned at Peking University in China where he worked on computer vision for medical applications, and at Preferred Networks in Japan where he worked on computer vision for autonomous driving. Detail: http://homes.sice.indiana.edu/stsutsui/.

Registration

You are all invited, free of charge. Registration in advance is required using the following form.

Past CODH Seminars

2019-01-08

9th CODH Seminar - Computer Vision with Limited Labeled Data

2018-11-22

8th CODH Seminar - Exploring Deep Learning for Classical Japanese Literature, Machine Creativity, and Recurrent World Models!

2018-07-31

7th CODH Seminar - Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer

2018-03-12

6th CODH Seminar: Historical Big Data - Challenges in Transforming Historical Documents to Structured Data for the Integrated Analysis of Records in the Past -

2017-12-04

5th CODH Seminar: Trustworthy Data Repositories - Forum for Sharing Practical Information about CoreTrustSeal Certification -

2017-07-27

4th CODH Seminar: A New Trend on Image Delivery in Digital Archives - IIIF's Potential for Standardization and Sophistication of Image Access -

2017-05-30

3rd CODH Seminar: Usage of DOI for Humanities - Assignment of DOI for Scholarly Resources such as Research Data and Museum Collections -

2017-02-10

2nd CODH Seminar: Old Japanese Character Challenge - Future of Machine Recognition and Human Transcription -

2017-01-23

1st CODH Seminar: Big Data and Digital Humanities