ISRS-DETR: Detection-Guided Click Propagation for Remote Sensing Interactive Segmentation
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the challenge of marking objects in very large and complex satellite images where objects are small and scattered. They note that previous methods treat all same-type objects in an image as one big target, which means clicking on one object doesn't help identify others of the same type nearby. To fix this, the authors designed a system called ISRS-DETR that uses object detection to spread one click's information to similar objects across the image, reducing the number of needed clicks. Their experiments show this method is more accurate and efficient on standard remote sensing datasets.
interactive segmentationremote sensing imageryobject detectionRF-DETR decoderclick annotationhigh-resolution imagesobject-level correlationDynamic Top-K Click SelectionNumber of Clicks per Imagesegmentation benchmarks
Authors
Thanh Duc Pham, Anh Nguyen, Duong Duc Hieu, Minh-Tan Pham
Abstract
Interactive segmentation reduces the prohibitive cost of pixel-level annotation by allowing users to delineate objects with a few clicks. However, applying this paradigm directly to remote sensing imagery is non-trivial: ultra-high resolutions, small object sizes, and sparse spatial distributions all degrade segmentation quality. Recent work has addressed the resolution barrier and achieved competitive results in interactive segmentation for remote sensing (ISRS). However, they treat all instances of a class within an image as a single objective target. Consequently, interactions spent on one object contribute nothing to its same-class neighbours, and satisfactory masks may demand up to 40 clicks per image, hindering the practicality of these frameworks. We observe that remote sensing scenes exhibit markedly strong inter-object correlation, meaning a single clicked object is highly informative about the rest of its category. Building on this, we propose ISRS-DETR, a detection-guided interactive segmentation framework that injects object-level evidence into both training and inference. Our ISRS-DETR employs an RF-DETR decoder with the interactive segmentation backbone to localise co-occurring same-class objects, and introduces a Dynamic Top-K Click Selection strategy that retains only reliable proposals and converts each into a simulated click, so one user interaction propagates across an entire class. Experiments on three standard remote sensing benchmarks show that ISRS-DETR achieves state-of-the-art accuracy while substantially reducing Number of Clicks per Image (NoC-I). All codes and data splits will be released for reproducibility upon acceptance.