GithubHelp home page GithubHelp logo

some questions about qaconv HOT 1 CLOSED

shengcailiao avatar shengcailiao commented on June 14, 2024
some questions

from qaconv.

Comments (1)

ShengcaiLiao avatar ShengcaiLiao commented on June 14, 2024 1

谢谢关注。

(1)QAconv对每个query的参数是不同的:CNN backbone的参数是一样的,只有QAConv层的卷积核参数不一样。测试时新的参数是从query feature map里得到的,可以看论文的示意图。Adaptive也就这个意思,指的是QAConv层的卷积核是根据query确定。

(2)query的每个位置都对应一个特异的卷积核。

(3)对,这个是QAConv高光的地方,对于局部匹配这个任务来说相当于是弱监督学习。原理上可以这么理解,是QAConv的这个机制和end-to-end的训练共同决定的。给定ID信息后,整个网络需要朝着正确识别ID的方向训练,然后在QAConv里寻找最大局部匹配分数的机制下,如果找到的匹配都是随机混乱的,那是很难完成ID识别任务的,因此网络会逐渐能找到一些靠谱的匹配去完成ID识别任务。

(4)这也是QAConv的机制决定的。传统的提取特征的CNN网络,提取的特征是个一维向量,是全局的响应,大致是抽象了训练集的一些显著的鉴别性特征,但“显著”和“鉴别性”在新domain下可能会变化。而QAConv的backbone提取的是保留了空间信息的2D特征图,因此这个局部响应会有更多的自由度;同时,QAConv的匹配方法的假设基础是同一个ID的不同图像具有一些相似的局部响应就行,而不是要求高度抽象了的全局特征要在特征空间中同ID聚拢,这样在新domain下只要这个假设还成立,就能匹配得好。

from qaconv.

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.