How to Reduce Change Detection to Semantic Segmentation

• URL: http://arxiv.org/abs/2206.07557v1
• Date: Wed, 15 Jun 2022 14:16:30 GMT
• Title: How to Reduce Change Detection to Semantic Segmentation
• Authors: Guo-Hua Wang, Bin-Bin Gao, Chengjie Wang
• Abstract summary: Change detection (CD) aims to identify changes that occur in an image pair taken different times. We propose a new paradigm that reduces CD to semantic segmentation. We also propose C-3PO, a network to detect changes at pixel-level.
• Score: 27.82117563417494
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Change detection (CD) aims to identify changes that occur in an image pair taken different times. Prior methods devise specific networks from scratch to predict change masks in pixel-level, and struggle with general segmentation problems. In this paper, we propose a new paradigm that reduces CD to semantic segmentation which means tailoring an existing and powerful semantic segmentation network to solve CD. This new paradigm conveniently enjoys the mainstream semantic segmentation techniques to deal with general segmentation problems in CD. Hence we can concentrate on studying how to detect changes. We propose a novel and importance insight that different change types exist in CD and they should be learned separately. Based on it, we devise a module named MTF to extract the change information and fuse temporal features. MTF enjoys high interpretability and reveals the essential characteristic of CD. And most segmentation networks can be adapted to solve the CD problems with our MTF module. Finally, we propose C-3PO, a network to detect changes at pixel-level. C-3PO achieves state-of-the-art performance without bells and whistles. It is simple but effective and can be considered as a new baseline in this field. Our code will be available.

Related papers

• Image Segmentation in Foundation Model Era: A Survey [99.19456390358211]
  Current research in image segmentation lacks a detailed analysis of distinct characteristics, challenges, and solutions associated with these advancements. This survey seeks to fill this gap by providing a thorough review of cutting-edge research centered around FM-driven image segmentation. An exhaustive overview of over 300 segmentation approaches is provided to encapsulate the breadth of current research efforts.
  arXiv  Detail & Related papers  (2024-08-23T10:07:59Z)
• Specialized Change Detection using Segment Anything [5.586191108738564]
  Change detection (CD) is a fundamental task in Earth observation. There is a growing need for specialized methods targeting specific changes relevant to particular applications while discarding the other changes. We propose a focused CD approach using the Segment Anything Model (SAM), a versatile vision foundation model.
  arXiv  Detail & Related papers  (2024-08-13T05:27:23Z)
• SeFi-CD: A Semantic First Change Detection Paradigm That Can Detect Any Change You Want [3.8287068443608567]
  This paper introduces a new CD paradigm, the semantic-first CD (SeFi-CD) paradigm. The core idea of SeFi-CD is to first perceive the dynamic semantics of interest and then visually search for change features related to the semantics. Experiments on public datasets demonstrate that the AUWCD outperforms the current state-of-the-art CD methods.
  arXiv  Detail & Related papers  (2024-07-13T12:49:58Z)
• MaskCD: A Remote Sensing Change Detection Network Based on Mask Classification [29.15203530375882]
  Change (CD) from remote sensing (RS) images using deep learning has been widely investigated in the literature. We propose MaskCD to detect changed areas by adaptively generating categorized masks from input image pairs. It reconstructs the desired changed objects by decoding the pixel-wise representations into learnable mask proposals.
  arXiv  Detail & Related papers  (2024-04-18T11:05:15Z)
• Pixel-Level Change Detection Pseudo-Label Learning for Remote Sensing Change Captioning [28.3763053922823]
  Methods for Remote Sensing Image Change Captioning (RSICC) perform well in simple scenes but exhibit poorer performance in complex scenes. We believe pixel-level CD is significant for describing the differences between images through language. Our method achieves state-of-the-art performance and validate that learning pixel-level CD pseudo-labels significantly contributes to change captioning.
  arXiv  Detail & Related papers  (2023-12-23T17:58:48Z)
• AF$_2$: Adaptive Focus Framework for Aerial Imagery Segmentation [86.44683367028914]
  Aerial imagery segmentation has some unique challenges, the most critical one among which lies in foreground-background imbalance. We propose Adaptive Focus Framework (AF$), which adopts a hierarchical segmentation procedure and focuses on adaptively utilizing multi-scale representations. AF$ has significantly improved the accuracy on three widely used aerial benchmarks, as fast as the mainstream method.
  arXiv  Detail & Related papers  (2022-02-18T10:14:45Z)
• Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation [91.30558794056056]
  Unsupervised domain adaptation (UDA) for semantic segmentation has been attracting attention recently. We present a novel framework based on three main design principles: discover, hallucinate, and adapt. We evaluate our solution on standard benchmark GTA to C-driving, and achieved new state-of-the-art results.
  arXiv  Detail & Related papers  (2021-10-08T13:20:09Z)
• A Few Guidelines for Incremental Few-Shot Segmentation [57.34237650765928]
  Given a pretrained segmentation model and few images containing novel classes, our goal is to learn to segment novel classes while retaining the ability to segment previously seen ones. We show how the main problems of end-to-end training in this scenario are. i) the drift of the batch-normalization statistics toward novel classes that we can fix with batch renormalization and. ii) the forgetting of old classes, that we can fix with regularization strategies.
  arXiv  Detail & Related papers  (2020-11-30T20:45:56Z)
• A Weakly Supervised Convolutional Network for Change Segmentation and Classification [91.3755431537592]
  We present W-CDNet, a novel weakly supervised change detection network that can be trained with image-level semantic labels. 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.
  arXiv  Detail & Related papers  (2020-11-06T20:20:45Z)
• CRNet: Cross-Reference Networks for Few-Shot Segmentation [59.85183776573642]
  Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images. With a cross-reference mechanism, our network can better find the co-occurrent objects in the two images. Experiments on the PASCAL VOC 2012 dataset show that our network achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-03-24T04:55:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.