paper-with-me

홈 › Papers

The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memory

2021-05-04 · ICCV 2021 10 · Sai Saketh Rambhatla, Rama Chellappa, Abhinav Shrivastava

We tackle object category discovery, which is the problem of discovering and localizing novel objects in a large unlabeled dataset. While existing methods show results on datasets with less cluttered scenes and fewer object instances per image, we present our results on the challenging COCO dataset. Moreover, we argue that, rather than discovering new categories from scratch, discovery algorithms can benefit from identifying what is already known and focusing their attention on the unknown. We propose a method that exploits prior knowledge about certain object types to discover new categories by leveraging two memory modules, namely Working and Semantic memory. We show the performance of our detector on the COCO minival dataset to demonstrate its in-the-wild capabilities.

📄 PDF Abstract BibTeX arXiv:2105.01652

Code (0)

등록된 구현이 없습니다.

Tasks

Object

Similar Papers 제목 키워드 기반

Beat-Event Detection in Action Movie Franchises

2015-08-15 · Danila Potapov, Matthijs Douze, Jerome Revaud, Zaid Harchaoui 외

While important advances were recently made towards temporally localizing and recognizing specific human actions or activities in videos, efficient detection and classification of long video chunks belonging to semantica…

ClassificationEvent DetectionGeneral Classification

Semi-supervised model-based clustering with controlled clusters leakage

2017-05-04 · Marek Śmieja, Łukasz Struski, Jacek Tabor

In this paper, we focus on finding clusters in partially categorized data sets. We propose a semi-supervised version of Gaussian mixture model, called C3L, which retrieves natural subgroups of given categories. In contra…

Clustering

Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery

2023-07-20 · ICCV 2023 1 · Hyungmin Kim, Sungho Suh, Daehwan Kim, Daun Jeong 외

Recent advances in deep learning have significantly improved the performance of various computer vision applications. However, discovering novel categories in an incremental learning scenario remains a challenging proble…

class-incremental learningClass Incremental LearningIncremental Learningunsupervised class-incremental learning

Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation

2021-07-07 · NeurIPS 2021 12 · Bingchen Zhao, Kai Han

In this paper, we tackle the problem of novel visual category discovery, i.e., grouping unlabelled images from new classes into different semantic partitions by leveraging a labelled dataset that contains images from oth…

Fine-Grained Visual RecognitionKnowledge Distillation

Class-incremental Novel Class Discovery

2022-07-18 · Subhankar Roy, Mingxuan Liu, Zhun Zhong, Nicu Sebe 외

We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained…

Incremental LearningKnowledge DistillationNovel Class Discovery