Cited 0 time in
Cited 0 time in
Weakly Supervised Learning with Deep Convolutional Neural Networks for Semantic Segmentation Understanding semantic layout of images with minimum human supervision
- Weakly Supervised Learning with Deep Convolutional Neural Networks for Semantic Segmentation Understanding semantic layout of images with minimum human supervision
- Hong, Seunghoon; Kwak, Su Ha; Han, Bohyung
- DGIST Authors
- Kwak, Su Ha
- Issue Date
- IEEE Signal Processing Magazine, 34(6), 39-49
- Article Type
- Annotated Training Data; Classification (of Information); Convolution; Convolutional Neural Network; Deep Neural Networks; Image Segmentation; Improve Performance; Large Scale Data Sets; Neural Networks; Object Boundaries; Object Detection; Semantic Segmentation; Semantic Web; Semantics; Visual Recognition; Weakly Supervised Learning
- Semantic segmentation is a popular visual recognition task whose goal is to estimate pixel-level object class labels in images. This problem has been recently handled by deep convolutional neural networks (DCNNs), and the state-of-theart techniques achieve impressive records on public benchmark data sets. However, learning DCNNs demand a large number of annotated training data while segmentation annotations in existing data sets are significantly limited in terms of both quantity and diversity due to the heavy annotation cost. Weakly supervised approaches tackle this issue by leveraging weak annotations such as image-level labels and bounding boxes, which are either readily available in existing large-scale data sets for image classification and object detection or easily obtained thanks to their low annotation costs. The main challenge in weakly supervised semantic segmentation then is the incomplete annotations that miss accurate object boundary information required to learn segmentation. This article provides a comprehensive overview of weakly supervised approaches for semantic segmentation. Specifically, we describe how the approaches overcome the limitations and discuss research directions worthy of investigation to improve performance. © 1991-2012 IEEE.
- Institute of Electrical and Electronics Engineers Inc.
There are no files associated with this item.
- Information and Communication EngineeringVision and Learning Lab(VL Lab)1. Journal Articles
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.