Giter Club home page Giter Club logo

cl_text's Introduction

CL_Text

This repository is an attempt to apply SCAN LOSS as discussed in SCAN: Learning to Classify Images without Labels on text data to perform text classification without any label.

SCAN paper discusses three step appraoch to do this task for images:

  • First train a model, on a contrastive loss, to get good feature embeddings.
  • Finetune the model obtained in first step on SCAN LOSS (defined in paper).
  • Again Finetune the model obtained in second step on Cross-Entropy loss by considering only confident predictions above a threshold as label.

Here instead of training the model, for the first step, from scratch, I am finetuning Pretrained SimCSE. And rest of the steps are followed as it is.

This repo is not complete yet and will be updated frequently. If interested to collaborate feel free to open an issue.

cl_text's People

Contributors

skrohit avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.