paper-with-me

Single-object discovery

5개 벤치마크 · 논문 10편 · 이 태스크의 논문 보기 →

Benchmarks

COCO_20k

결과 10개

VOC_all

결과 3개

Object Discovery

결과 2개

VOC12

결과 2개

VOC_6x2

결과 2개

Most implemented

Large-Scale Unsupervised Object Discovery

2021-06-12 · 구현 1개

Papers

PEEKABOO: Hiding parts of an image for unsupervised object localization

2024-07-24 · Hasib Zunair, A. Ben Hamza

Localizing objects in an unsupervised manner poses significant challenges due to the absence of key visual information such as the appearance, type and number of objects, as well as the lack of labeled object classes typ…

Objectobject-detectionObject DetectionObject Discovery+4

MOVE: Unsupervised Movable Object Segmentation and Detection

2022-10-14 · Adam Bielski, Paolo Favaro

We introduce MOVE, a novel method to segment objects without any form of supervision. MOVE exploits the fact that foreground objects can be shifted locally relative to their initial position and result in realistic (undi…

Class-agnostic Object DetectionObjectobject-detectionObject Detection+7

K-means for unsupervised instance segmentation using a self-supervised transformer

2022-10-04 · Pattern Recognition 2022 10 · Lim SeongTaek, Park JaeEon, Lee MinYoung, Lee HongChul

Instance segmentation is a fundamental task in computer vision that assigns every pixel to an appropriate class and localizes objects into bounding boxes. However, collecting pixel-level segmentation labels is more reso…

Instance SegmentationObject DetectionObject DiscoverySegmentation+3

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

2022-02-23 · CVPR 2022 1 · Yangtao Wang, Xi Shen, Shell Hu, Yuan Yuan 외

Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based appr…

Objectobject-detectionObject DetectionObject Discovery+5

Localizing Objects with Self-Supervised Transformers and no Labels

2021-09-29 · Oriane Siméoni, Gilles Puy, Huy V. Vo, Simon Roburin 외

Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer p…

ObjectObject DiscoverySingle-object discoveryWeakly-Supervised Object Localization

Large-Scale Unsupervised Object Discovery

2021-06-12 · NeurIPS 2021 12 · Huy V. Vo, Elena Sizikova, Cordelia Schmid, Patrick Pérez 외

Existing approaches to unsupervised object discovery (UOD) do not scale up to large datasets without approximations that compromise their performance. We propose a novel formulation of UOD as a ranking problem, amenable …

Multi-object discoveryObjectObject DiscoverySingle-object discovery

전체 10편 보기 →