Git Product home page Git Product logo

Comments (2)

bbepoch avatar bbepoch commented on July 30, 2024

Mainly because the one-to-one matching strategy and the definition of HOI instance. For example, given an image, their is a person sitting on a horse, and the GT contains 3 HOI categories, e.g. (person, ride, horse), (person, sit_on, horse), (person, straddle, horse).

In training, the model directly outputs 100 HOI instances, the ground truth size is also 100 with 3 positive instances and 97 null padding. That is to say, there are only 3 slots responsible for the positive predictions.

In inference, if given this image, only 3 of the 100 slots are actived, so, after filterring, the model only outputs 3 HOI instances.

To summary, in the set prediction view, we don't think the original GT is one element with 3 labels, but 3 different elements.

The 'Appendix A: Illustration of Inference Process' part may help.

I hope it helped you, thanks.

from hoitransformer.

feather820 avatar feather820 commented on July 30, 2024

Thanks, it helps me a lot

from hoitransformer.

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.