DeepAI AI Chat
Log In Sign Up

Neuron-level Selective Context Aggregation for Scene Segmentation

11/22/2017
by   Zhenhua Wang, et al.
Shandong University
Hebrew University of Jerusalem
Tel Aviv University
0

Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation. In this paper, we introduce a neuron-level Selective Context Aggregation (SCA) module for scene segmentation, comprised of a contextual dependency predictor and a context aggregation operator. The dependency predictor is implicitly trained to infer contextual dependencies between different image regions. The context aggregation operator augments local representations with global context, which is aggregated selectively at each neuron according to its on-the-fly predicted dependencies. The proposed mechanism enables data-driven inference of contextual dependencies, and facilitates context-aware feature learning. The proposed method improves strong baselines built upon VGG16 on challenging scene segmentation datasets, which demonstrates its effectiveness in modeling context information.

READ FULL TEXT

page 6

page 7

page 8

04/06/2021

DCANet: Dense Context-Aware Network for Semantic Segmentation

As the superiority of context information gradually manifests in advance...
04/03/2020

Context Prior for Scene Segmentation

Recent works have widely explored the contextual dependencies to achieve...
04/05/2021

Hierarchical Pyramid Representations for Semantic Segmentation

Understanding the context of complex and cluttered scenes is a challengi...
03/09/2020

Context-Aware Domain Adaptation in Semantic Segmentation

In this paper, we consider the problem of unsupervised domain adaptation...
03/25/2020

SCATTER: Selective Context Attentional Scene Text Recognizer

Scene Text Recognition (STR), the task of recognizing text against compl...
03/13/2023

Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model

Despite the success of deep neural network (DNN) on sequential data (i.e...