paper-with-me

Papers

Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation

2016-12-08 · Xianming Liu, Amy Zhang, Tobias Tiecke, Andreas Gros, Thomas S. Huang

Learning from weakly-supervised data is one of the main challenges in machine learning and computer vision, especially for tasks such as image semantic segmentation where labeling is extremely expensive and subjective. In this paper, we propose a novel neural network architecture to perform weakly-supervised learning by suppressing irrelevant neuron activations. It localizes objects of interest by learning from image-level categorical labels in an end-to-end manner. We apply this algorithm to a practical challenge of transforming satellite images into a map of settlements and individual buildings. Experimental results show that the proposed algorithm achieves superior performance and efficiency when compared with various baseline models.

📄 PDF Abstract BibTeX arXiv:1612.02766

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SegmentationWeakly-supervised Learning

Similar Papers 제목 키워드 기반

Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation

2019-05-29 · Zhengqiang Zhang, Shujian Yu, Shi Yin, Qinmu Peng 외

Weakly-supervised semantic segmentation aims to assign each pixel a semantic category under weak supervisions, such as image-level tags. Most of existing weakly-supervised semantic segmentation methods do not use any fee…

SegmentationSemantic SegmentationSuperpixelsWeakly supervised Semantic Segmentation+1

Weakly Supervised Instance Segmentation by Deep Community Learning

2020-01-30 · Jaedong Hwang, Seohyun Kim, Jeany Son, Bohyung Han

We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks. This task is formulated as a combination of weakly supervised object detection and semantic segmentatio…

Image-level Supervised Instance SegmentationInstance Segmentationobject-detectionObject Detection+4

Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation

2023-08-09 · Lei Zhu, Hangzhou He, Xinliang Zhang, Qian Chen 외

End-to-end weakly supervised semantic segmentation aims at optimizing a segmentation model in a single-stage training process based on only image annotations. Existing methods adopt an online-trained classification branc…

ClassificationSegmentationSemantic SegmentationWeakly supervised segmentation+2

Two-Phase Learning for Weakly Supervised Object Localization

2017-08-07 · ICCV 2017 10 · Dahun Kim, Donghyeon Cho, Donggeun Yoo, In So Kweon

Weakly supervised semantic segmentation and localiza- tion have a problem of focusing only on the most important parts of an image since they use only image-level annota- tions. In this paper, we solve this problem funda…

ObjectObject LocalizationSegmentationSemantic Segmentation+5

Convolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation

2018-07-24 · Rania Briq, Michael Moeller, Juergen Gall

Weakly supervised semantic segmentation has been a subject of increased interest due to the scarcity of fully annotated images. We introduce a new approach for solving weakly supervised semantic segmentation with deep Co…

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation