paper-with-me

Papers

A Weakly Supervised Convolutional Network for Change Segmentation and Classification

2020-11-06 · Philipp Andermatt, Radu Timofte

Fully supervised change detection methods require difficult to procure pixel-level labels, while weakly supervised approaches can be trained with image-level labels. However, most of these approaches require a combination of changed and unchanged image pairs for training. Thus, these methods can not directly be used for datasets where only changed image pairs are available. We present W-CDNet, a novel weakly supervised change detection network that can be trained with image-level semantic labels. Additionally, W-CDNet can be trained with two different types of datasets, either containing changed image pairs only or a mixture of changed and unchanged image pairs. Since we use image-level semantic labels for training, we simultaneously create a change mask and label the changed object for single-label images. W-CDNet employs a W-shaped siamese U-net to extract feature maps from an image pair which then get compared in order to create a raw change mask. The core part of our model, the Change Segmentation and Classification (CSC) module, learns an accurate change mask at a hidden layer by using a custom Remapping Block and then segmenting the current input image with the change mask. The segmented image is used to predict the image-level semantic label. The correct label can only be predicted if the change mask actually marks relevant change. This forces the model to learn an accurate change mask. We demonstrate the segmentation and classification performance of our approach and achieve top results on AICD and HRSCD, two public aerial imaging change detection datasets as well as on a Food Waste change detection dataset. Our code is available at https://github.com/PhiAbs/W-CDNet .

📄 PDF Abstract BibTeX arXiv:2011.03577

Code (1)

PhiAbs/W-CDNet 공식 구현 tf

Tasks

Change DetectionClassificationGeneral Classification

Methods 이 논문이 사용한 방법론

Siamese Network 설명 없음
Siamese U-Net Siamese U-Net model with a pre-trained ResNet34 architecture as an encoder for data efficient Change Detection
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Weakly-supervised fire segmentation by visualizing intermediate CNN layers

2021-11-16 · Milad Niknejad, Alexandre Bernardino

Fire localization in images and videos is an important step for an autonomous system to combat fire incidents. State-of-art image segmentation methods based on deep neural networks require a large number of pixel-annotat…

Image SegmentationSegmentationSemantic SegmentationWeakly supervised segmentation

Weakly Supervised Segmentation of Hyper-Reflective Foci with Compact Convolutional Transformers and SAM2

2025-01-10 · Olivier Morelle, Justus Bisten, Maximilian W. M. Wintergerst, Robert P. Finger 외

Weakly supervised segmentation has the potential to greatly reduce the annotation effort for training segmentation models for small structures such as hyper-reflective foci (HRF) in optical coherence tomography (OCT). Ho…

Multiple Instance LearningSegmentationWeakly supervised segmentation

WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation

2017-07-01 · CVPR 2017 7 · Thibaut Durand, Taylor Mordan, Nicolas Thome, Matthieu Cord

This paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features. Our model is trained using only global image lab…

General Classificationimage-classificationImage ClassificationObject Localization+4

Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation

2018-06-01 · CVPR 2018 6 · Yunchao Wei, Huaxin Xiao, Honghui Shi, Zequn Jie 외

Despite remarkable progress, weakly supervised segmentation methods are still inferior to their fully supervised counterparts. We obverse that the performance gap mainly comes from the inability of producing dense and in…

ClassificationGeneral ClassificationObjectObject Localization+4

Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation

2018-05-11 · CVPR 2018 · Yunchao Wei, Huaxin Xiao, Honghui Shi, Zequn Jie 외

Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produ…

ObjectObject LocalizationSegmentationSemantic Segmentation+2