pytorch, pre-trained model, image segmentation, supervised learning,

U2Net

Wen-Chieh-Lee Wen-Chieh-Lee Follow Sep 05, 2020 · 3 mins read
U2Net
Share this

SOD

SOD (Salient Object Detection) is a topics in deep learning that by given a image, SOD can automatically segmentize the most interested objects of the image without any hints. SOD learns how human see the interested objects by detecting the denisity of feature points and segmentize the most dense parts. So far, U2Net provide a state of art performance.

First results of U2Net

These are the first results of the U2Net on target benchmark images. For the full results can be checked in Chimay-SOD1 and asubset Chimay-SOD2 can be found.

IMG_0754.JPG IMG_0754.JPG with U2Net Toucan.jpg Toucan.jpg with U2Net IMG_1192.jpg IMG_1192.jpg with U2Net 1.jpg 1.jpg with U2Net 2.jpg 2.jpg with U2Net 3.jpg 3.jpg with U2Net 4.jpg 4.jpg with U2Net 5.jpg 5.jpg with U2Net 6.jpg 6.jpg with U2Net 7.jpg 7.jpg with U2Net 8.jpg 8.jpg with U2Net 9.jpg 9.jpg with U2Net 10.jpg 10.jpg with U2Net 11.jpg 11.jpg with U2Net 12.jpg 12.jpg with U2Net 13.jpg 13.jpg with U2Net 14.jpg 14.jpg with U2Net 15.jpg 15.jpg with U2Net IMG_1613.jpg IMG_1613.jpg with U2Net IMG_8282.JPG IMG_8282.JPG with U2Net IMG_8544.jpg IMG_8544.jpg with U2Net IMG_0124.jpg IMG_0124.jpg with U2Net IMG_8609.JPG IMG_8609.JPG with U2Net

Image sliders

In this page, image slider for jekyll and its js code is used for image slider. Also a Jekyll Ideal Image Slider Include Demo shows the possiblity of Ideal Image Slider.

References

Wen-Chieh-Lee
Written by Wen-Chieh-Lee
Senior Software Architect