KSG-Net: Key-Sparse and Global-Context Learning for Maritime 3D Ship Detection

• URL: http://arxiv.org/abs/2609.02077v1
• Date: Wed, 02 Sep 2026 04:06:40 GMT
• Title: KSG-Net: Key-Sparse and Global-Context Learning for Maritime 3D Ship Detection
• Abstract summary: This paper focuses on two key challenges in maritime LiDAR perception: weak feature representation for small and sparse vessels, and insufficient global structural modeling for large vessels.<n>We propose KSG-Net, a Key-Sparse and Global-Context learning network for maritime 3D ship detection.<n>The core idea is to jointly enhance local discriminative features and global structural awareness within a unified fully sparse detection framework.
• Score: 14.109391283358626
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate 3D ship detection in maritime environments is critical for autonomous navigation, yet remains challenging due to large-scale vessel variations, sparse point clouds of small vessels, and severe sea-clutter interference. Existing methods, primarily based on 2D features or dense representations, struggle to balance detection accuracy and computational efficiency, while sparse 3D detectors designed for road scenes generalize poorly to maritime scenarios. This paper focuses on two key challenges in maritime LiDAR perception: weak feature representation for small and sparse vessels, and insufficient global structural modeling for large vessels due to the limited receptive field of local sparse convolutions. To address these issues, we propose KSG-Net, a Key-Sparse and Global-Context learning network for maritime 3D ship detection. The core idea is to jointly enhance local discriminative features and global structural awareness within a unified fully sparse detection framework. Specifically, a Key Sparse Multi-scale Aggregation (KSMA) module is designed to enhance the representation of small and sparse vessels by selecting informative key voxels and aggregating cross-scale neighborhood features. Furthermore, a Global Context Aggregation (GCA) module is introduced to capture long-range geometric dependencies through scene-level context modeling with gated residual interactions, thereby improving the representation of large vessels. Extensive experiments on the Thames River vessel dataset and simulated datasets demonstrate that KSG-Net consistently outperforms existing methods in multi-scale vessel detection and exhibits strong robustness in complex maritime environments.

Related papers

• FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction [63.738631229597274]
  Vision-based 3D occupancy prediction fundamentally relies on the 2D-to-3D view transformation.<n>Current paradigms predominantly utilize explicit physical projection, which artificially restricts the routing matrix to strict, sparse camera rays.<n>We propose Factorized Dense Routing (FDR) to break this bottleneck.<n>Our framework achieves state-the-art performance on the Occ3D-nuScenes and Occ3D-Waymo benchmarks.
  arXiv  Detail & Related papers  (2026-07-04T11:12:42Z)
• Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention [9.838390322438535]
  We design a CNN-Mamba fusion network that integrates polygon scanning mamba and space-frequency collaborative attention mechanism for the detection of small vessels.<n>Considering that the traditional mamba architecture with horizontal-vertical scanning may compromise the topological integrity of target structures, we present a polygon scanning visual state space model (PS-VSS) to identify small vessel structural features.
  arXiv  Detail & Related papers  (2026-05-11T13:53:51Z)
• WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects [68.44670476527155]
  WUTDet is a large-scale ship detection dataset with 100,576 images and 381,378 annotated ship instances.<n>We systematically evaluate 20 baseline models from three mainstream detection architectures, namely CNN, Transformer, and Mamba.<n>Results on Ship-GEN show that models trained on WUTDet exhibit stronger generalization under different data distributions.
  arXiv  Detail & Related papers  (2026-04-09T03:28:05Z)
• UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction [83.48950950780554]
  Building extraction from remote sensing images is a challenging task due to the complex structure variations of buildings.<n>Existing methods employ convolutional or self-attention blocks to capture the multi-scale features in the segmentation models.<n>We present an Uncertainty-Aggregated Global-Local Fusion Network (UAGLNet) to exploit high-quality global-local visual semantics.
  arXiv  Detail & Related papers  (2025-12-15T02:59:16Z)
• TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decoder [66.22997415145467]
  This paper presents a joint completion and detection framework that improves the detection feature in sparse areas.<n> Specifically, we propose TransBridge, a novel transformer-based up-sampling block that fuses the features from the detection and completion networks.<n>The results show that our framework consistently improves end-to-end 3D object detection, with the mean average precision (mAP) ranging from 0.7 to 1.5 across multiple methods.
  arXiv  Detail & Related papers  (2025-12-12T00:08:03Z)
• Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection [54.1960918379255]
  Neptune-X is a data-centric generative-selection framework for maritime object detection.<n>X-to-Maritime is a multi-modality-conditioned generative model that synthesizes diverse and realistic maritime scenes.<n>Our approach sets a new benchmark in maritime scene synthesis, significantly improving detection accuracy.
  arXiv  Detail & Related papers  (2025-09-25T04:59:02Z)
• COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection [13.236592868442678]
  We propose a novel framework for tiny object detection in multimodal Red-Green-Blue-Thermal (RGBT) imagery.<n>Cross-Layer Fusion Module fuses high-level visible and low-level thermal features for enhanced semantic and spatial accuracy.<n>Dynamic Alignment and Scale Refinement module corrects cross-modal spatial misalignments.<n>GeoShape Similarity Measure is used for better localization.
  arXiv  Detail & Related papers  (2025-08-13T06:30:03Z)
• Convolutional Feature Enhancement and Attention Fusion BiFPN for Ship Detection in SAR Images [3.1536619649037716]
  This paper proposes a novel feature enhancement and fusion framework named C-AFBiFPN.<n>C-AFBiFPN constructs a Convolutional Feature Enhancement (CFE) module following the backbone network.<n>C-AFBiFPN innovatively integrates BiFormer attention within the fusion strategy of BiFPN, creating the AFBiFPN network.
  arXiv  Detail & Related papers  (2025-06-18T08:14:28Z)
• Enhancing, Refining, and Fusing: Towards Robust Multi-Scale and Dense Ship Detection [7.208605594108282]
  We propose a novel framework, Center-Aware SAR Ship Detector (CASS-Det), for robust multi-scale and densely packed ship detection.<n>CASS-Det integrates three key innovations: (1) a center enhancement module (CEM) that employs rotational convolution to emphasize ship centers; (2) a neighbor attention module (NAM) that leverages cross-layer dependencies to refine ship boundaries in densely populated scenes; and (3) a cross-connected feature pyramid network (CC-FPN) that enhances multi-scale feature fusion.
  arXiv  Detail & Related papers  (2025-01-10T15:33:37Z)
• PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection [59.355022416218624]
  integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. We propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN) PVAFN uses a multi-pooling strategy to integrate both multi-scale and region-specific information effectively.
  arXiv  Detail & Related papers  (2024-08-26T19:43:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.