Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

2021-04-04 · CVPR 2021 1 · Xinggang Wang, Jiapei Feng, Bin Hu, Qi Ding, Longjin Ran, Xiaoxin Chen, Wenyu Liu

Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation. The BoxCaseg model is jointly trained using box-supervised images and salient images in a multi-task learning manner. The fine-annotated salient images provide class-agnostic and precise object localization guidance for box-supervised images. The object masks predicted by a pretrained BoxCaseg model are refined via a novel merged and dropped strategy as proxy ground truth to train a Mask R-CNN for weakly-supervised instance segmentation. Only using $7991$ salient images, the weakly-supervised Mask R-CNN is on par with fully-supervised Mask R-CNN on PASCAL VOC and significantly outperforms previous state-of-the-art box-supervised instance segmentation methods on COCO. The source code, pretrained models and datasets are available at \url{https://github.com/hustvl/BoxCaseg}.

📄 PDF Abstract BibTeX arXiv:2104.01526

Code (0)

등록된 구현이 없습니다.

Tasks

Box-supervised Instance Segmentation Instance Segmentation Multi-Task LearningObjectObject Localization Segmentation Semantic Segmentation Weakly-supervised instance segmentation

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Mask R-CNN Mask R-CNN extends Faster R-CNN to solve instance segmentation tasks. It achieves this by adding a branch for predicting an…

Prior to Segment: Foreground Cues for Weakly Annotated Classes in Partially Supervised Instance Segmentation

2020-11-23 · ICCV 2021 10 · David Biertimpel, Sindi Shkodrani, Anil S. Baslamisli, Nóra Baka

Instance segmentation methods require large datasets with expensive and thus limited instance-level mask labels. Partially supervised instance segmentation aims to improve mask prediction with limited mask labels by util…

Instance Segmentation Segmentation Semantic Segmentation

Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation

2021-01-01 · ICCV 2021 10 · Yunhang Shen, Liujuan Cao, Zhiwei Chen, Baochang Zhang 외

Weakly supervised instance segmentation (WSIS) with only image-level labels has recently drawn much attention. To date, bottom-up WSIS methods refine discriminative cues from classifiers with sophisticated multi-stag…

Instance Segmentation object-detection Object Detection Segmentation+4

BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation

2021-03-16 · CVPR 2021 1 · Jungbeom Lee, Jihun Yi, Chaehun Shin, Sungroh Yoon

Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object. Existing methods typically depend on a class-agnostic mask generator, which …

Box-supervised Instance Segmentation Instance Segmentation Object Segmentation+4

Learning Instance Activation Maps for Weakly Supervised Instance Segmentation

2019-06-01 · CVPR 2019 6 · Yi Zhu, Yanzhao Zhou, Huijuan Xu, Qixiang Ye 외

Discriminative region responses residing inside an object instance can be extracted from networks trained with image-level label supervision. However, learning the full extent of pixel-level instance response in a weakly…

Image-level Supervised Instance Segmentation Instance Segmentation Object object-detection+7

Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instances

2020-07-18 · ECCV 2020 8 · Aditya Arun, C. V. Jawahar, M. Pawan Kumar

Recent approaches for weakly supervised instance segmentations depend on two components: (i) a pseudo label generation model that provides instances which are consistent with a given annotation; and (ii) an instance segm…

Image-level Supervised Instance Segmentation Instance Segmentation Pseudo Label Segmentation+2