Skip to Main content Skip to Navigation
Conference papers

QFabric: Multi-Task Change Detection Dataset

Sagar Verma 1 Akash Panigrahi 2 Siddharth Gupta 2
1 OPIS - OPtimisation Imagerie et Santé
CVN - Centre de vision numérique, Inria Saclay - Ile de France
Abstract : Detecting change through multi-image, multi-date remote sensing is essential to developing and understanding of global conditions. Despite recent advancements in remote sensing realized through deep learning, novel methods for accurate multi-image change detection remain unrealized. Recently, several promising methods have been proposed to address this topic, but a paucity of publicly available data limits the methods that can be assessed. In particular, there exists limited work on categorizing the nature and status of change across an observation period. This paper introduces the first labeled dataset available for such a task. We present an open-source change detection dataset, termed QFabric, with 450,000 change polygons annotated across 504 locations in 100 different cities covering a wide range of geographies and urban fabrics. QFabric is a temporal multi-task dataset with 6 change types and 9 change status classes. The geography and environment metadata around each polygon provides context that can be leveraged to build robust deep neural networks. We apply multiple benchmarks on our dataset for change detection, change type and status classification tasks. Project page: Land Cleared Construction Midway Construction Midway Construction Done Operational Commercial Industrial.
Complete list of metadata
Contributor : Sagar Verma <>
Submitted on : Wednesday, July 21, 2021 - 4:19:06 PM
Last modification on : Saturday, July 24, 2021 - 3:44:58 AM


Files produced by the author(s)


  • HAL Id : hal-03294534, version 1


Sagar Verma, Akash Panigrahi, Siddharth Gupta. QFabric: Multi-Task Change Detection Dataset. EARTHVISION 2021 Workshops - Large Scale Computer Vision for Remote Sensing Imagery: in conjunction with the Conference on Computer Vision and Pattern Recognition (CVPR 2021), Jun 2021, Virtual, France. ⟨hal-03294534⟩



Record views


Files downloads