Lightweight SAR Ship Detection via Contrastive Distillation

• URL: http://arxiv.org/abs/2605.30380v2
• Date: Mon, 01 Jun 2026 03:28:35 GMT
• Title: Lightweight SAR Ship Detection via Contrastive Distillation
• Abstract summary: This work presents the first transformer-based SAR ship detector knowledge distillation framework in SAR domain.<n>The framework is architecture-agnostic in the sense it provides a common region-level distillation interface for two-stage one-stage and transformer-based detectors.<n> Experiments on the SSDD and HRSID benchmarks demonstrate that the proposed method yields substantial improvements for two-stage detectors.
• Score: 0.19116784879310023
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep convolutional and transformer-based detectors achieve strong performance for SAR ship detection but are often computationally prohibitive for real-time or onboard deployment. Lightweight models offer improved efficiency yet struggle to capture the complex structural relationships inherent in SAR backscatter. Most existing SAR knowledge-distillation approaches rely on feature or logit matching, which enforces localized activation similarity while neglecting the geometric relationships among object representations. We propose a Structured Unified Relational knowledGE distillation framework for SAR Ship detection (SURGE) that transfers relational geometry from a powerful teacher detector to a compact student detector using a contrastive InfoNCE objective in a shared projection embedding space. To the best of our knowledge, this work presents the first transformer-based SAR ship detector knowledge distillation framework in SAR domain. The framework is architecture-agnostic in the sense that it provides a common region-level distillation interface for two-stage, one-stage and transformer-based detectors without modifying their deployed architectures. Experiments on the SSDD and HRSID benchmarks demonstrate that the proposed method yields substantial improvements for two-stage detectors, achieving up to 6.2 mAP and 8.0 AP75 gains over baseline student and even surpassing teacher performance

Related papers

• SARATR-X-v2: Scale-Aware Structural Pre-Training for SAR Foundation Models [43.156720517756405]
  A SAR pre-training target should satisfy two conditions to produce transferable representations.<n> physics-grounded stability favors fixed operators, while semantic scale compatibility favors data-driven composition.<n> SARATR-X-v2 reconciles both within a single design.
  arXiv  Detail & Related papers  (2026-07-25T14:51:05Z)
• REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling [56.888597798431704]
  Open-World Object Detection (OWOD) requires detectors to identify previously unseen objects as unknown and incrementally incorporate them into the set of known categories.<n>Existing frameworks rely heavily on exemplar replay to mitigate catastrophic forgetting, but in some real applications, storing raw data conflicts with data access restrictions and leads to data exposure risks.<n>We propose REAL-OW, a novel rehearsal-free framework that decouples incremental knowledge through a collaborative adapter architecture.
  arXiv  Detail & Related papers  (2026-07-03T06:38:54Z)
• GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval [54.741349848771144]
  GeoMamba is a geometry-driven framework for optical-SAR fine-grained retrieval.<n>GFI module enhances cross-modal feature interaction and incorporates structural priors.<n>GeoMamba outperforms existing methods, achieving 63.3% mAP and 77.0% Rank-1 accuracy in all-to-all retrieval setting.
  arXiv  Detail & Related papers  (2026-05-19T12:08:09Z)
• Source-Free Object Detection with Detection Transformer [59.33653163035064]
  Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data.<n>Most existing SFOD approaches are either confined to conventional object detection (OD) models like Faster R-CNN or designed as general solutions without tailored adaptations for novel OD architectures, especially Detection Transformer (DETR)<n>In this paper, we introduce Feature Reweighting ANd Contrastive Learning NetworK (FRANCK), a novel SFOD framework specifically designed to perform query-centric feature enhancement for DETRs.
  arXiv  Detail & Related papers  (2025-10-13T07:35:04Z)
• Large-Scale Model Enabled Semantic Communication Based on Robust Knowledge Distillation [45.347078403677216]
  Large-scale models (LSMs) can be an effective framework for semantic representation and understanding.<n>However, their direct deployment is often hindered by high computational complexity and resource requirements.<n>This paper proposes a novel knowledge distillation based semantic communication framework.
  arXiv  Detail & Related papers  (2025-08-04T07:47:18Z)
• O2Former:Direction-Aware and Multi-Scale Query Enhancement for SAR Ship Instance Segmentation [0.3611754783778107]
  Instance segmentation of ships in synthetic aperture radar (SAR) imagery is critical for applications such as maritime monitoring, environmental analysis, and national security.<n> SAR ship images present challenges including scale variation, object density, and fuzzy target boundary.<n>We propose O2Former, a tailored instance segmentation framework that extends Mask2Former by fully leveraging the structural characteristics of SAR imagery.
  arXiv  Detail & Related papers  (2025-06-13T16:06:51Z)
• HA-RDet: Hybrid Anchor Rotation Detector for Oriented Object Detection [0.0]
  Oriented object detection in aerial images poses a significant challenge due to their varying sizes and orientations.<n>We propose the Hybrid-Anchor Rotation Detector (HA-RDet), which combines the advantages of both anchor-based and anchor-free schemes for oriented object detection.<n>HA-RDet achieves competitive accuracies, including 75.41 mAP on DOTA-v1, 65.3 mAP on DIOR-R, and 90.2 mAP on HRSC2016.
  arXiv  Detail & Related papers  (2024-12-18T22:26:15Z)
• Physics-Guided Detector for SAR Airplanes [48.11882103050703]
  We propose a novel physics-guided detector (PGD) learning paradigm for SAR airplanes. It comprehensively investigate their discreteness and variability to improve the detection performance. The experiments demonstrate the flexibility and effectiveness of the proposed PGD.
  arXiv  Detail & Related papers  (2024-11-19T07:41:09Z)
• Multi-scale direction-aware SAR object detection network via global information fusion [18.997878517911378]
  This paper proposes SAR-Net, a novel framework specifically designed for global fusion of direction-aware information in SAR object detection. UCM and DAM enable efficient global information fusion and transmission. Experiments demonstrate the effectiveness of SAR-Net, achieving state-of-the-art results on aircraft and ship datasets.
  arXiv  Detail & Related papers  (2023-12-28T10:40:11Z)
• SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment [76.80165589520385]
  We name our method SEA (SEmantic-aware Alignment) distillation given the nature of abstracting dense fine-grained information. It achieves new state-of-the-art results on the challenging object detection task on both one- and two-stage detectors.
  arXiv  Detail & Related papers  (2022-03-02T04:24:05Z)
• Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection [50.53262868498824]
  Shape deformation of targets in SAR image due to random orientation and partial information loss is an essential challenge in SAR ship detection. We propose a data augmentation method to train a deep network that is robust to partial information loss within the targets.
  arXiv  Detail & Related papers  (2022-02-14T07:01:01Z)

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.