2019

InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting

Fang, Hao-Shu, Sun, Jianhua, Wang, Runzhong et al.

Understand

Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation.

To enlarge the training set and increase the diversity, previous methods have investigated using data annotation from other domain (e.g.
bbox, point) in a weakly supervised mechanism.
In this paper, we present a simple, efficient and effective method to augment the training set using the existing instance mask annotations.

Built on

Visual thinking
Rudolf Arnheim · 1969
Earlier work this paper cites.
Contour integration by the human visual system: evidence for a local “association field”
David J Field, Anthony Hayes, and Robert F Hess · 1993
Earlier work this paper cites.
Watershed-based segmentation and region merging
André Bleau and L Joshua Leon · 2000
Earlier work this paper cites.
Navier-stokes, fluid dynamics, and image and video inpainting
Marcelo Bertalmio, Andrea L Bertozzi, and Guillermo Sapiro · 2001
Earlier work this paper cites.
A stochastic grammar of images
Song-Chun Zhu, David Mumford, et al · 2007
Earlier work this paper cites.
The pascal visual object classes (voc) challenge
Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman · 2010
Earlier work this paper cites.
Semantic contours from inverse detectors
Bharath Hariharan, Pablo Arbelaez, Lubomir Bourdev, Subhransu Maji, and Jitendra Malik · 2011
Earlier work this paper cites.
A global sampling method for alpha matting
Kaiming He, Christoph Rhemann, Carsten Rother, Xiaoou Tang, and Jian Sun · 2011
Earlier work this paper cites.
Segmentation of unknown objects in indoor environments
Andreas Richtsfeld, Thomas Mörwald, Johann Prankl, Michael Zillich, and Markus Vincze · 2012
Earlier work this paper cites.
Visual perception: An introduction
Nicholas Wade and Mike Swanston · 2013
Earlier work this paper cites.
Complex background subtraction by pursuing dynamic spatio-temporal models
Liang Lin, Yuanlu Xu, Xiaodan Liang, and Jianhuang Lai · 2014
Earlier work this paper cites.
Microsoft coco: Common objects in context
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick · 2014
Earlier work this paper cites.
Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation
Jifeng Dai, Kaiming He, and Jian Sun · 2015
Earlier work this paper cites.
Learning to segment object candidates
Pedro O Pinheiro, Ronan Collobert, and Piotr Dollár · 2015
Earlier work this paper cites.
Faster R-CNN: Towards real-time object detection with region proposal networks
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun · 2015
Earlier work this paper cites.

Similar

What’s the point: Semantic segmentation with point supervision
Amy Bearman, Olga Russakovsky, Vittorio Ferrari, and Li Fei-Fei · 2016
Cited alongside, same era.
The cityscapes dataset for semantic urban scene understanding
Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele · 2016
Cited alongside, same era.
Instance-sensitive fully convolutional networks
Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, and Jian Sun · 2016
Cited alongside, same era.
Instance-aware semantic segmentation via multi-task network cascades
Jifeng Dai, Kaiming He, and Jian Sun · 2016
Cited alongside, same era.
Scribblesup: Scribble-supervised convolutional networks for semantic segmentation
Di Lin, Jifeng Dai, Jiaya Jia, Kaiming He, and Jian Sun · 2016
Cited alongside, same era.
Cut, paste and learn: Surprisingly easy synthesis for instance detection
Debidatta Dwibedi, Ishan Misra, and Martial Hebert · 2017
Cited alongside, same era.
Rmpe: Regional multi-person pose estimation
Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, and Cewu Lu · 2017
Cited alongside, same era.
Look into person: Self-supervised structure-sensitive learning and a new benchmark for human parsing
Ke Gong, Xiaodan Liang, Dongyu Zhang, Xiaohui Shen, and Liang Lin · 2017
Cited alongside, same era.
Mask r-cnn
Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick · 2017
Cited alongside, same era.
Fully convolutional instance-aware semantic segmentation
Yi Li, Haozhi Qi, Jifeng Dai, Xiangyang Ji, and Yichen Wei · 2017
Cited alongside, same era.
Feature pyramid networks for object detection
Tsung-Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie · 2017
Cited alongside, same era.
Saliency-aware video object segmentation
Wenguan Wang, Jianbing Shen, Ruigang Yang, and Fatih Porikli · 2017
Cited alongside, same era.

Then

mmdetection
Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, Chen Change Loy, and Dahua Lin · 2018
Later among the works it cites.
Masklab: Instance segmentation by refining object detection with semantic and direction features
Liang-Chieh Chen, Alexander Hermans, George Papandreou, Florian Schroff, Peng Wang, and Hartwig Adam · 2018
Later among the works it cites.
Learning segmentation masks with the independence prior
Original
Songmin Dai, Xiaoqiang Li, Lu Wang, Pin Wu, Weiqin Tong, and Yimin Chen · 2018
Later among the works it cites.
Modeling visual context is key to augmenting object detection datasets
Nikita Dvornik, Julien Mairal, and Cordelia Schmid · 2018
Later among the works it cites.
Weakly and semi supervised human body part parsing via pose-guided knowledge transfer
Hao-Shu Fang, Guansong Lu, Xiaolin Fang, Jianwen Xie, Yu-Wing Tai, and Cewu Lu · 2018
Later among the works it cites.
Cooperative holistic scene understanding: Unifying 3d object, layout, and camera pose estimation
Siyuan Huang, Siyuan Qi, Yinxue Xiao, Yixin Zhu, Ying Nian Wu, and Song-Chun Zhu · 2018
Later among the works it cites.
Learning human-object interactions by graph parsing neural networks
Siyuan Qi, Wenguan Wang, Baoxiong Jia, Jianbing Shen, and Song-Chun Zhu · 2018
Later among the works it cites.
Find and focus: Retrieve and localize video events with natural language queries
Dian Shao, Yu Xiong, Yue Zhao, Qingqiu Huang, Yu Qiao, and Dahua Lin · 2018
Later among the works it cites.
Srda: Generating instance segmentation annotation via scanning, reasoning and domain adaptation
Wenqiang Xu, Yonglu Li, and Cewu Lu · 2018
Later among the works it cites.
Crowdpose: Efficient crowded scenes pose estimation and a new benchmark
Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, and Cewu Lu · 2019
Closest in time.
Transferable interactiveness knowledge for human-object interaction detection
Yong-Lu Li, Siyuan Zhou, Xijie Huang, Liang Xu, Ze Ma, Hao-Shu Fang, Yanfeng Wang, and Cewu Lu · 2019
Closest in time.
See more, know more: Unsupervised video object segmentation with co-attention siamese networks
Xiankai Lu, Wenguan Wang, Chao Ma, Jianbing Shen, Ling Shao, and Fatih Porikli · 2019
Closest in time.
Salient object detection in the deep learning era: An in-depth survey
Original
Wenguan Wang, Qiuxia Lai, Huazhu Fu, Jianbing Shen, and Haibin Ling · 2019
Closest in time.
Explicit shape encoding for real-time instance segmentation
Original
Wenqiang Xu, Haiyang Wang, Fubo Qi, and Cewu Lu · 2019
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…