Giter VIP home page Giter VIP logo

Comments (5)

vealocia avatar vealocia commented on July 17, 2024

Q1: YES. We apply HungarianMatcher to get the corresponding queries, and then use ground-truth boxes to extract RoI features.
Q2: NO. The target frames only take part in tracking head at training phase.
Q3: NO.

from queryinst.

DKWarcher avatar DKWarcher commented on July 17, 2024

Q1: YES. We apply HungarianMatcher to get the corresponding queries, and then use ground-truth boxes to extract RoI features. Q2: NO. The target frames only take part in tracking head at training phase. Q3: NO.

Thanks a lot!

from queryinst.

Haelles avatar Haelles commented on July 17, 2024

Q1: YES. We apply HungarianMatcher to get the corresponding queries, and then use ground-truth boxes to extract RoI features.
Q2: NO. The target frames only take part in tracking head at training phase.
Q3: NO.

In the Dynamic Instance Embedding part, do the key frame share queries($q_{t-1}^{*}$ in formula(4) ) with the reference frame? Or another HungarianMatcher is needed to get the reference frame's exclusive queries?

from queryinst.

vealocia avatar vealocia commented on July 17, 2024

Yes, we inference querytrack on reference frame (with torch.no_grad()) and apply another HungarianMatcher to get the assignment between queries and ground-truths.

Q1: YES. We apply HungarianMatcher to get the corresponding queries, and then use ground-truth boxes to extract RoI features.
Q2: NO. The target frames only take part in tracking head at training phase.
Q3: NO.

In the Dynamic Instance Embedding part, do the key frame share queries($q_{t-1}^{*}$ in formula(4) ) with the reference frame? Or another HungarianMatcher is needed to get the reference frame's exclusive queries?

from queryinst.

Haelles avatar Haelles commented on July 17, 2024

Yes, we inference querytrack on reference frame (with torch.no_grad()) and apply another HungarianMatcher to get the assignment between queries and ground-truths.

Q1: YES. We apply HungarianMatcher to get the corresponding queries, and then use ground-truth boxes to extract RoI features.
Q2: NO. The target frames only take part in tracking head at training phase.
Q3: NO.

In the Dynamic Instance Embedding part, do the key frame share queries($q_{t-1}^{*}$ in formula(4) ) with the reference frame? Or another HungarianMatcher is needed to get the reference frame's exclusive queries?

Thank you! And could you please tell me the weights of ClassificationCost, BBoxL1Cost and IoUCost when getting the assignment between queries and ground-truth bboxes of the reference frame? Thanks again.

from queryinst.

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.