Skip to content
This organization was marked as archived by an administrator on Nov 3, 2023. It is no longer maintained.
@ncd-research

ncd-research

Novel Category Discovery (NCD) algorithm research repository

NCD Research Space

Hello👋 This is a repository for research of Novel Category Discovery algorithm.

Novel Category Discovery

  • [DTC] Han, Kai, et al. "Learning to discover novel visual categories via deep transfer clustering." (ICCV 2019) [paper] [code]
    • The first paper to define the Novel Category Discovery task.
  • [RS] Han, Kai, et al. "Automatically discovering and learning new visual categories with ranking statistics." (ICLR 2020) [paper]
  • [AutoNovel] Kai Han, et al., "Autonovel: Automatically discovering and learning novel visual categories." (TPAMI 2021) [paper] [code]
    • I would recommend this paper to understand research trends on the Novel Category Discovery task.
  • [DualRS] Zhao, Bingchen, and Kai Han. "Novel visual category discovery with dual ranking statistics and mutual knowledge distillation." (NeurIPS 2021) [paper] [code]
  • [NCL] Zhong, Zhun, et al., "Neighborhood Contrastive Learning for Novel Class Discovery." (CVPR 2021) [paper] [code]
  • [OpenMix] Zhong, Zhun, et al., "OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in an Open World." (CVPR 2021) [paper]
  • [UNO] Fini, Enrico, et al., "A unified objective for novel class discovery." (ICCV 2021) [paper] [code]
  • [MP, MM] Chi, Haoang, et al., "Meta discovery: Learning to discover novel classes given very limited data." (ICLR 2022) [paper] [code]
  • [NCDwF] Gaurav Aggarwal, et al., "Novel Class Discovery without Forgetting." (ECCV 2022) [paper]

Generalized Category Discovery

a.k.a. Open-World Semi-Supervised Learning

  • [GCD] Vaze, Sagar, et al., "Generalized Category Discovery." (CVPR 2022) [paper] [code]
    • The first paper to define the Generalized Category Discovery task.
  • [ComEx] Yang, Muli, et al., "Divide and Conquer: Compositional Experts for Generalized Novel Class Discovery." (CVPR 2022) [paper] [code]
  • [XCon] Fei, Yixin, et al., "XCon: Learning with Experts for Fine-grained Category Discovery." (2022) [paper] [code]
  • [SimGCD] Xin Wen, et al., "A Simple Parametric Classification Baseline for Generalized Category Discovery." (2022) [paper][code]
  • [PromptCAL] Sheng Zhan, et al., "PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery." (under review, 2022) [paper][code]
  • [MIB] Florent Chiaroni, et al., "Mutual Information-based Generalized Category Discovery." (2022) [paper]
  • [MI] Chuyu Zhang, et al., "Mutual Information-guided Knowledge Transfer for Open-World Semi-Supervised Learning ." (2022) [paper]
  • [GPC] Bingchen Zhao, et al., "Generalized Category Discovery via Adaptive GMMs without Knowing the Class Number." (2022) [paper]

(Updates: 22.08.31) There is a well-organized reference repository here.

Popular repositories

  1. SimGCD SimGCD Public archive

    Forked from CVMI-Lab/SimGCD

    Reproduction of SimGCD

    Python 1

  2. .github .github Public archive

  3. GCD GCD Public archive

    Forked from sgvaze/generalized-category-discovery

    Reproduce: "Generalized Category Discovery" (CVPR 2022)

    Python

  4. AutoNovel AutoNovel Public archive

    Forked from k-han/AutoNovel

    Reproduce: "Automatically Discovering and Learning New Visual Categories with Ranking Statistics" by Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman (ICLR 2020)

    Python

  5. OpenLDN OpenLDN Public archive

    Forked from nayeemrizve/OpenLDN

    Reproduce: "OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning" (ECCV 2022)

    Python

  6. PromptCAL PromptCAL Public archive

    Forked from sheng-eatamath/PromptCAL

    Reproduction of PromptCAL

    Python

Repositories

Showing 6 of 6 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…