Background-Mixed Augmentation for Weakly Supervised Change Detection

  title={Background-Mixed Augmentation for Weakly Supervised Change Detection},
  author={Rui Huang and Ruofei Wang and Qing Guo and Jieda Wei and Yuxiang Zhang and Wei Fan and Yang Liu},
Change detection (CD) is to decouple object changes ( i.e ., ob- ject missing or appearing) from background changes ( i.e ., environment variations) like light and season variations in two images captured in the same scene over a long time span, presenting critical applications in disaster management, ur- ban development, etc . In particular, the endless patterns of background changes require detectors to have a high gener- alization against unseen environment variations, making this task… 

Figures and Tables from this paper



Object-level change detection with a dual correlation attention-guided detector

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.

Weakly Supervised Silhouette-based Semantic Scene Change Detection

This paper presents a novel semantic scene change detection scheme with only weak supervision that proposes a new siamese network structure with the introduction of correlation layer and creates a publicly available dataset for semantic change detection.

Use of Generative Adversarial Network for Cross-Domain Change Detection

This paper addresses the problem of cross-domain change detection from a novel perspective of image-to-image translation by leveraging a generative adversarial network (GAN) and considers the use of visual place recognition as a method for mining more appropriate reference images over the space of virtual images.

KeepAugment: A Simple Information-Preserving Data Augmentation Approach

This paper empirically shows that the standard data augmentation methods may introduce distribution shift and consequently hurt the performance on unaugmented data during inference, and proposes a simple yet effective approach, dubbed KeepAugment, to increase the fidelity of augmented images.

A Weakly Supervised Convolutional Network for Change Segmentation and Classification

W-CDNet is presented, a novel weakly supervised change detection network that can be trained with image-level semantic labels and achieves top results on AICD and HRSCD, two public aerial imaging change detection datasets as well as on a Food Waste change detection dataset.

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Patches are cut and pasted among training images where the ground truth labels are also mixed proportionally to the area of the patches, and CutMix consistently outperforms state-of-the-art augmentation strategies on CIFAR and ImageNet classification tasks, as well as on ImageNet weakly-supervised localization task.

Fully Convolutional Change Detection Framework with Generative Adversarial Network for Unsupervised, Weakly Supervised and Regional Supervised Change Detection

  • Chen WuBo DuL. Zhang
  • Computer Science, Environmental Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2023
A fully convolutional change detection framework with generative adversarial network is proposed, to conclude unsupervised, weakly supervised, regional supervised, and fully supervised change detection tasks into one framework.

Generative Adversarial Networks for Change Detection in Multispectral Imagery

This letter proposes an unsupervised change detection method based on generative adversarial networks (GANs), which has the ability of recovering the training data distribution from noise input and demonstrates the effectiveness and robustness of the proposed method.

Let There Be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer

This paper proposes a framework to alleviate the accuracy decline when object detection is taken to adverse conditions by using image translation method, and utilizes Kernel Prediction Network (KPN) based method to refine the nighttime to daytime image translation.