2019 IEEE/CVF International Conference on Computer Vision (ICCV) 2019
DOI: 10.1109/iccv.2019.00685
|View full text |Cite
|
Sign up to set email alerts
|

Adaptive Context Network for Scene Parsing

Abstract: Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally. However, in this paper, we find that the context demands are varying from different pixels or regions in each image. Based on this observation, we propose an Adaptive Context Network (AC-Net) to capture the pixel-aware contexts by a competitive fusion of global context and local context according to d… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
77
0

Year Published

2019
2019
2021
2021

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 141 publications
(77 citation statements)
references
References 35 publications
0
77
0
Order By: Relevance
“…In order to obtain global contextual affinity, we should firstly aggregate global information for generating global contextual feature representations. It has been proven that the global average pooling (GAP) can effectively capture global contextual information without complex computational redundancy 43,44,46,47 . Therefore, the feature map B is fed into a GAP layer to generate a global representation gboldRC×1×1.…”
Section: Methodsmentioning
confidence: 99%
“…In order to obtain global contextual affinity, we should firstly aggregate global information for generating global contextual feature representations. It has been proven that the global average pooling (GAP) can effectively capture global contextual information without complex computational redundancy 43,44,46,47 . Therefore, the feature map B is fed into a GAP layer to generate a global representation gboldRC×1×1.…”
Section: Methodsmentioning
confidence: 99%
“…Scene segmentation (or scene parsing, semantic segmentation) is one of the fundamental problems in computer vision and has drawn lots of attentions. Recently, thanks to the great success of Convolutional Neural Networks (CNNs) in computer vision [42,68,71,52,25,72,27,80,26], lots of CNNs based segmentation works have been proposed and have achieved great progress [29,22,81,83,84,70,60]. For example, Long et al [54] introduce the fully convolutional networks (FCN) in which the fully connected layers in standard CNNs are transformed to convolutional layers.…”
Section: Related Work 21 Scene Segmentationmentioning
confidence: 99%
“…These methods rely on the last layer for scaling features which has reduced receptive field. To counter this challenge [36] and [37] leverage intermediate features to understand scaling along with last layer. These techniques use dilation and pooling, which result in patterned scaling.…”
Section: Related Workmentioning
confidence: 99%