TL;DR
This paper introduces a novel deep learning framework for semantic change detection in high-resolution aerial images, featuring new loss functions, attention modules, and architecture, achieving state-of-the-art results on benchmark datasets.
Contribution
It presents a new architecture with innovative attention modules, loss functions, and feature extraction units specifically designed for semantic change detection.
Findings
Achieved state-of-the-art F1 and IoU scores on LEVIRCD and WHU datasets.
Validated new feature extraction blocks on CIFAR10.
Demonstrated effectiveness of the proposed architecture in change detection tasks.
Abstract
Change detection, i.e. identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of change that appear at different times in input images. Here, we propose a reliable deep learning framework for the task of semantic change detection in very high-resolution aerial images. Our framework consists of a new loss function, new attention modules, new feature extraction building blocks, and a new backbone architecture that is tailored for the task of semantic change detection. Specifically, we define a new form of set similarity, that is based on an iterative evaluation of a variant of the Dice coefficient. We use this similarity metric to define a new loss function as well as a new spatial and channel convolution Attention layer (the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsAverage Pooling · 1x1 Convolution · Global Average Pooling · Kaiming Initialization · *Communicated@Fast*How Do I Communicate to Expedia? · Batch Normalization · Residual Connection · Max Pooling · Residual Block · Convolution
