paper-with-me

Papers

Unsupervised object discovery for instance recognition

2017-09-14 · Oriane Siméoni, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum

Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The descriptors derived from the salient regions improve particular object retrieval, most noticeably in a large collections containing small objects.

📄 PDF Abstract BibTeX arXiv:1709.04725

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalObjectObject DiscoveryRetrieval

Similar Papers 제목 키워드 기반

Image Segmentation-based Unsupervised Multiple Objects Discovery

2022-12-20 · Sandra Kara, Hejer Ammar, Florian Chabot, Quoc-Cuong Pham

Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, botto…

Class-agnostic Object DetectionImage SegmentationObjectobject-detection+4

Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery

2025-09-02 · Xinrui Gong, Oliver Hahn, Christoph Reich, Krishnakant Singh 외 arxiv

Unsupervised multi-object discovery (MOD) aims to detect and localize distinct object instances in visual scenes without any form of human supervision. Recent approaches leverage object-centric learning (OCL) and motion …

Multi-object discoveryMotion Segmentation

Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision

2021-04-02 · CVPR 2021 1 · Zhenzhen Weng, Mehmet Giray Ogut, Shai Limonchik, Serena Yeung

Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new dom…

Instance SegmentationNovel Object DetectionSegmentationSemantic Segmentation

Unsupervised Discovery of 3D Physical Objects

2021-01-01 · ICLR 2021 1 · Yilun Du, Kevin A. Smith, Tomer Ullman, Joshua B. Tenenbaum 외

We study the problem of unsupervised physical object discovery. Unlike existing frameworks that aim to learn to decompose scenes into 2D segments purely based on each object's appearance, we explore how physics, especial…

3D geometryObjectObject DiscoveryPosition

Enhancing Object Discovery for Unsupervised Instance Segmentation and Object Detection

2025-08-04 · Xingyu Feng, Hebei Gao, Hong Li arxiv

We propose Cut-Once-and-LEaRn (COLER), a simple approach for unsupervised instance segmentation and object detection. COLER first uses our developed CutOnce to generate coarse pseudo labels, then enables the detector to …

Unsupervised Instance SegmentationUnsupervised Object LocalizationObject SegmentationObject Detection