Giter VIP home page Giter VIP logo

Comments (3)

LiheYoung avatar LiheYoung commented on September 27, 2024

Hi, thanks for noticing it and raising the question.

Generally speaking, the annotations of labeled images in Table.1 and Table.2 are of different qualities.

Specifically, the Pascal VOC 2012 training set originally contains 1,464 high-quality annotations. Later it is augmented by extra 9,118 lower-quality annotations from the SBD dataset to form 10,582 image-masks pairs.

The labeled images in Table.1 are randomly selected from the augmented training set with 10,582 imaages in total, while the labeled images in Table.2 are selected from the high-quality original training set with 1,464 images in total. Please refer to the first sentence of the table caption for difference. By the way, the unlabeled images are both the remaining images in the augmented training set.

The settings of Table.1 follow the mainstream practice in recent works like Context-aware Consistency , while Table.2 follows the state-of-the-art method PseudoSeg.

from st-plusplus.

 avatar commented on September 27, 2024

That's clarify a lot.
Thanks very much!

from st-plusplus.

geek-APTX4869 avatar geek-APTX4869 commented on September 27, 2024

The experiments in Table 1 were performed on which division of Pascal VOC?

from st-plusplus.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.