Plug-and-play DISep: Separating dense instances for scene-to-pixel weakly-supervised change detection in high-resolution remote sensing images

Abstract

Change Detection (CD) focuses on identifying specific pixel-level landscape changes in multi-temporal remote sensing images. The process of obtaining pixel-level annotations for CD is generally both time-consuming and labor-intensive. Faced with this annotation challenge, there has been a growing interest in research on Weakly-Supervised Change Detection (WSCD). WSCD aims to detect pixel-level changes using only scene-level (i.e., image-level) change labels, thereby offering a more cost-effective approach. Despite considerable efforts to precisely locate changed regions, existing WSCD methods often encounter the problem of “instance lumping” under scene-level supervision, particularly in scenarios with a dense distribution of changed instances (i.e., changed objects). In these scenarios, unchanged pixels between changed instances are also mistakenly identified as changed, causing multiple changes to be mistakenly viewed as one. In practical applications, this issue prevents the accurate quantification of the number of changes. To address this issue, we propose a Dense Instance Separation (DISep) method as a plug-and-play solution, refining pixel features from a unified instance perspective under scene-level supervision. Specifically, our DISep comprises a three-step iterative training process: (1) Instance Localization: We locate instance candidate regions for changed pixels using high-pass class activation maps. (2) Instance Retrieval: We identify and group these changed pixels into different instance IDs through connectivity searching. Then, based on the assigned instance IDs, we extract corresponding pixel-level features on a per-instance basis. (3) Instance Separation: We introduce a separation loss to enforce intra-instance pixel consistency in the embedding space, thereby ensuring separable instance feature representations. The proposed DISep adds only minimal training cost and no inference cost. It can be seamlessly integrated to enhance existing WSCD methods. We achieve state-of-the-art performance by enhancing three Transformer-based and four ConvNet-based methods on the LEVIR-CD, WHU-CD, DSIFN-CD, SYSU-CD, and CDD datasets. Additionally, our DISep can be used to improve fully-supervised change detection methods. Code is available at https://github.com/zhenghuizhao/Plug-and-Play-DISep-for-Change-Detection.