Large Selective Kernel Network for Remote Sensing Object Detection

Recent research on remote sensing object detection has largely focused on improving the representation of oriented bounding boxes but has overlooked the unique prior knowledge presented in remote sensing scenarios. Such prior knowledge can be useful because tiny remote sensing objects may be mistakenly detected without referencing a sufficiently long-range context, and the long-range context required by different types of objects can vary. In this paper, we take these priors into account and propose the Large Selective Kernel Network (LSKNet). LSKNet can dynamically adjust its large spatial receptive field to better model the ranging context of various objects in remote sensing scenarios. To the best of our knowledge, this is the first time that large and selective kernel mechanisms have been explored in the field of remote sensing object detection. Without bells and whistles, LSKNet sets new state-of-the-art scores on standard benchmarks, i.e., HRSC2016 (98.46\% mAP), DOTA-v1.0 (81.85\% mAP) and FAIR1M-v1.0 (47.87\% mAP). Based on a similar technique, we rank 2nd place in 2022 the Greater Bay Area International Algorithm Competition. Code is available at

PDF Abstract ICCV 2023 PDF ICCV 2023 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Object Detection In Aerial Images DOTA LSKNet-T mAP 81.37% # 4
Object Detection In Aerial Images DOTA LSKNet-S* mAP 81.85% # 1
Object Detection In Aerial Images DOTA LSKNet-S mAP 81.64% # 3
Oriented Object Detection DOTA 1.0 LSKNet-S* mAP 81.85 # 2
Object Detection In Aerial Images HRSC2016 LSKNet-S mAP-07 90.65 # 1
mAP-12 98.46 # 1
Semantic Segmentation ISPRS Potsdam LSKNet-S Overall Accuracy 92.0 # 3
Mean F1 93.1 # 5
Mean IoU 87.2 # 4
Semantic Segmentation ISPRS Vaihingen LSKNet-S Overall Accuracy 93.6 # 1
Average F1 91.8 # 2
Category mIoU 85.1 # 1
Semantic Segmentation ISPRS Vaihingen LSKNet-T Overall Accuracy 93.6 # 1
Average F1 91.7 # 3
Category mIoU 84.9 # 2
Semantic Segmentation LoveDA LSKNet-S Category mIoU 54.0 # 3
Semantic Segmentation LoveDA LSKNet-T Category mIoU 53.2 # 4
Semantic Segmentation UAVid LSKNet-T Mean IoU 69.3 # 2
Semantic Segmentation UAVid LSKNet-S Mean IoU 70.0 # 1