paper-with-me

Papers

GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture

2021-06-03 · Weijin Zhu, Yao Shen, Linfeng Yu, Lizeth Patricia Aguirre Sanchez

Recent studies on unsupervised object detection based on spatial attention have achieved promising results. Models, such as AIR and SPAIR, output "what" and "where" latent variables that represent the attributes and locations of objects in a scene, respectively. Most of the previous studies concentrate on the "where" localization performance; however, we claim that acquiring "what" object attributes is also essential for representation learning. This paper presents a framework, GMAIR, for unsupervised object detection. It incorporates spatial attention and a Gaussian mixture in a unified deep generative model. GMAIR can locate objects in a scene and simultaneously cluster them without supervision. Furthermore, we analyze the "what" latent variables and clustering process. Finally, we evaluate our model on MultiMNIST and Fruit2D datasets and show that GMAIR achieves competitive results on localization and clustering compared to state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2106.01722

Code (1)

shaohua0116/MultiDigitMNIST 공식 구현

Tasks

ClusteringObjectobject-detectionObject DetectionRepresentation LearningUnsupervised Object Detection

Similar Papers 제목 키워드 기반

Spatial Attention Pyramid Network for Unsupervised Domain Adaptation

2020-03-29 · ECCV 2020 8 · Cong-Cong Li, Dawei Du, Libo Zhang, Longyin Wen 외

Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, and semantic segmentation, which aims to alleviate performance degradation caused by domain-sh…

Domain AdaptationInstance Segmentationobject-detectionObject Detection+3

Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

2020-11-14 · Zhen Zhao, Yuhong Guo, Jieping Ye

Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain detection model that exploits the annotate…

ObjectObject DetectionUnsupervised Domain Adaptation

Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement

2018-02-14 · Pattern Recognition 2018 2 · YijunYan, JinchangRen, GenyunSun, HuiminZhao 외

Visual attention is a kind of fundamental cognitive capability that allows human beings to focus on the region of interests (ROIs) under complex natural environments. What kind of ROIs that we pay attention to mainly dep…

object-detectionObject DetectionSaliency DetectionSalient Object Detection

Benchmarking Unsupervised Object Representations for Video Sequences

2020-06-12 · Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel 외

Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-ce…

BenchmarkingClusteringMulti-Object TrackingObject+4

CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks

2022-06-04 · Ruiqing Yan, Fan Zhang, Mengyuan Huang, Wu Liu 외

Detection of object anomalies is crucial in industrial processes, but unsupervised anomaly detection and localization is particularly important due to the difficulty of obtaining a large number of defective samples and t…

Anomaly DetectionUnsupervised Anomaly Detection