paper-with-me

Papers

Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization

2019-10-04 · Wenju Xu, Yuanwei Wu, Wenchi Ma, Guanghui Wang

In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set from the training dataset is a collection of background, object parts, and objects. Several strategies are taken to adaptively eliminate the noisy proposals and generate pseudo object-level annotations for the weakly labeled dataset. A multiple instance learning (MIL) algorithm enhanced by mask-out strategy is adopted to collect the class-specific object proposals, which are then utilized to adapt a pre-trained classification network to a detection network. In addition, the detection results from the detection network are re-weighted by jointly considering the detection scores and the overlap ratio of proposals in a proposal subset optimization framework. The optimal proposals work as object-level labels that enable a pseudo-strongly supervised dataset for training the detection network. Consequently, we establish a fully adaptive detection network. Extensive evaluations on the PASCAL VOC 2007 and 2012 datasets demonstrate a significant improvement compared with the state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:1910.02101

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingMultiple Instance LearningObjectObject LocalizationWeakly-Supervised Object Localization

Similar Papers 제목 키워드 기반

Adaptively Denoising Proposal Collection forWeakly Supervised Object Localization

2019-10-04 · arXiv 2019 10 · Wenju Xu, Yuanwei Wu, Wenchi Ma, Guanghui Wang

In this paper, we address the problem of weakly supervisedobject localization (WSL), which trains a detection network on the datasetwith only image-level annotations. The proposed approach is built on theobservation that…

DenoisingMultiple Instance LearningObjectObject Localization+1

You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection

2019-06-01 · CVPR 2019 6 · Krishna Kumar Singh, Yong Jae Lee

We propose a novel way of using videos to obtain high precision object proposals for weakly-supervised object detection. Existing weakly-supervised detection approaches use off-the-shelf proposal methods like edge boxes…

Objectobject-detectionObject DetectionRegion Proposal+1

Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy

2016-10-05 · Dan Barnes, Will Maddern, Ingmar Posner

We present a weakly-supervised approach to segmenting proposed drivable paths in images with the goal of autonomous driving in complex urban environments. Using recorded routes from a data collection vehicle, our propose…

Autonomous DrivingSegmentationSemantic SegmentationWeakly supervised segmentation

Weakly Supervised Region Proposal Network and Object Detection

2018-09-01 · ECCV 2018 9 · Peng Tang, Xinggang Wang, Angtian Wang, Yongluan Yan 외

The Convolutional Neural Network (CNN) based region proposal generation method (i.e. region proposal network), trained using bounding box annotations, is an essential component in modern fully supervised object detectors…

Objectobject-detectionObject DetectionRegion Proposal+1

Prompt3D: Random Prompt Assisted Weakly-Supervised 3D Object Detection

2024-01-01 · CVPR 2024 1 · Xiaohong Zhang, Huisheng Ye, Jingwen Li, Qinyu Tang 외

The prohibitive cost of annotations for fully supervised 3D indoor object detection limits its practicality. In this work we propose Random Prompt Assisted Weakly-supervised 3D Object Detection termed as Prompt3D a w…

3D Object Detectionobject-detectionObject DetectionScene Generation