Corpus ID: 53963567

Weakly Supervised Silhouette-based Semantic Change Detection

  title={Weakly Supervised Silhouette-based Semantic Change Detection},
  author={Ken Sakurada},
This paper presents a novel semantic change detection scheme with only weak supervision. A straightforward approach for this task is to train a semantic change detection network directly from a large-scale dataset in an end-to-end manner. However, a specific dataset for this new task, which is usually labor-intensive and time-consuming, becomes indispensable. To avoid this problem, we propose to train this kind of network from existing datasets by dividing this task into change detection and… Expand
PGA-SiamNet: Pyramid Feature-Based Attention-Guided Siamese Network for Remote Sensing Orthoimagery Building Change Detection
The proposed end-to-end network, called the pyramid feature-based attention-guided Siamese network (PGA-SiamNet), is trained to capture possible changes using a convolutional neural network in a pyramid and effectively improved the long-range dependencies of the features by utilizing various attention mechanisms. Expand
DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing
This paper proposes a network adaptation framework to achieve Panoramic Annular Semantic Segmentation (PASS), which allows to re-use conventional pinhole-view image datasets, enabling modern segmentation networks to comfortably adapt to panoramic images. Expand
Hierarchical Paired Channel Fusion Network for Street Scene Change Detection
A novel Hierarchical Paired Channel Fusion Network (HPCFNet) is presented, which utilizes the adaptive fusion of paired feature channels to adapt to the scale and location diversities of the scene change regions. Expand


Street-view change detection with deconvolutional networks
This work proposes a system for performing structural change detection in street-view videos captured by a vehicle-mounted monocular camera over time, and introduces a new urban change detection dataset which is an order of magnitude larger than existing datasets and contains challenging changes due to seasonal and lighting variations. Expand
Learning deep structured network for weakly supervised change detection
This paper presents a weakly supervised approach that needs only image-level labels to simultaneously detect and localize changes in a pair of images and defines a CRF model to incorporate the local differences and context with the dense connections between individual pixels. Expand
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
This paper generates a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations, and conducts experiments with DCNNs that show how the inclusion of SYnTHIA in the training stage significantly improves performance on the semantic segmentation task. Expand
Learning to Adapt Structured Output Space for Semantic Segmentation
A multi-level adversarial network is constructed to effectively perform output space domain adaptation at different feature levels and it is shown that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality. Expand
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
This paper proposes a simple approach to generate large annotated instance datasets with minimal effort and outperforms existing synthesis approaches and when combined with real images improves relative performance by more than 21% on benchmark datasets. Expand
Building Detection from Satellite Imagery using Ensemble of Size-Specific Detectors
A simple, but effective multi-task model that learns multiple detectors each of which is dedicated to a specific size of buildings, and implicitly utilizes context information by simultaneously training road extraction task along with building detection task. Expand
Dense Optical Flow based Change Detection Network Robust to Difference of Camera Viewpoints
A change detection convolutional neural network utilizing dense optical flow between input images to improve the robustness to the difference between camera viewpoints is proposed and outperforms state-of-the-art change detection algorithms. Expand
CDnet 2014: An Expanded Change Detection Benchmark Dataset
The latest release of the dataset is presented, which includes 22 additional videos spanning 5 new categories that incorporate challenges encountered in many surveillance settings and highlights strengths and weaknesses of these methods and identifies remaining issues in change detection. Expand
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes, aiming to significantly further the development of state-of-the-art methods for visual road-scene understanding. Expand
Forest Change Detection in Incomplete Satellite Images With Deep Neural Networks
This paper analyzes imagery data from remote sensing satellites to detect forest cover changes over a period of 29 years, and automatically learns region representations using a deep neural network in a data-driven fashion. Expand