Multitask Learning for SAR Ship Detection with Gaussian-Mask Joint Segmentation

• URL: http://arxiv.org/abs/2411.13847v1
• Date: Thu, 21 Nov 2024 05:10:41 GMT
• Title: Multitask Learning for SAR Ship Detection with Gaussian-Mask Joint Segmentation
• Abstract summary: This paper proposes a multitask learning framework for SAR ship detection, consisting of object detection, speckle suppression, and target segmentation tasks. An angle classification loss with aspect ratio weighting is introduced to improve detection accuracy by addressing angular periodicity and object proportions. The speckle suppression task uses a dual-feature fusion attention mechanism to reduce noise and fuse shallow and denoising features, enhancing robustness. The target segmentation task, leveraging a rotated Gaussian-mask, aids the network in extracting target regions from cluttered backgrounds and improves detection efficiency with pixel-level predictions.
• Score: 20.540873039361102
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Detecting ships in synthetic aperture radar (SAR) images is challenging due to strong speckle noise, complex surroundings, and varying scales. This paper proposes MLDet, a multitask learning framework for SAR ship detection, consisting of object detection, speckle suppression, and target segmentation tasks. An angle classification loss with aspect ratio weighting is introduced to improve detection accuracy by addressing angular periodicity and object proportions. The speckle suppression task uses a dual-feature fusion attention mechanism to reduce noise and fuse shallow and denoising features, enhancing robustness. The target segmentation task, leveraging a rotated Gaussian-mask, aids the network in extracting target regions from cluttered backgrounds and improves detection efficiency with pixel-level predictions. The Gaussian-mask ensures ship centers have the highest probabilities, gradually decreasing outward under a Gaussian distribution. Additionally, a weighted rotated boxes fusion (WRBF) strategy combines multi-direction anchor predictions, filtering anchors beyond boundaries or with high overlap but low confidence. Extensive experiments on SSDD+ and HRSID datasets demonstrate the effectiveness and superiority of MLDet.

Related papers

• SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection [13.697178700187402]
  Ship detection in Synthetic Aperture Radar (SAR) imagery is fundamentally challenged by inherent coherent speckle noise.<n>We propose SARES-DEIM, a domain-aware detection framework grounded in the DEtection TRansformer (DETR) paradigm.<n>Central to our approach is SARESMoE, a module leveraging a sparse gating mechanism to selectively route features toward specialized frequency and wavelet experts.
  arXiv  Detail & Related papers  (2026-04-05T14:15:39Z)
• CCDNet: Learning to Detect Camouflage against Distractors in Infrared Small Target Detection [22.490046328258444]
  Infrared target detection tasks have critical applications in areas like wilderness rescue and maritime search.<n> detecting infrared targets is challenging due to their low contrast and tendency to blend into complex backgrounds, effectively camouflaging themselves.<n>We propose a novel textbfCamouflage-aware textbfCounter-textbfDistraction textbfNetwork (CCDNet) in this paper.
  arXiv  Detail & Related papers  (2026-03-31T03:51:51Z)
• DCCS-Det: Directional Context and Cross-Scale-Aware Detector for Infrared Small Target [4.318503966844226]
  Infrared small target detection (IRSTD) is critical for applications like remote sensing and surveillance.<n>We propose DCCS-Det, a novel detector that incorporates a Dual-stream Saliency Enhancement (DSE) block and a Latent-aware Semantic Extraction and Aggregation (LaSEA) module.<n>Experiments show that DCCS-Det achieves state-of-the-art detection accuracy with competitive efficiency across multiple datasets.
  arXiv  Detail & Related papers  (2026-01-23T03:53:59Z)
• SDCoNet: Saliency-Driven Multi-Task Collaborative Network for Remote Sensing Object Detection [7.016133328153285]
  In remote sensing images, complex backgrounds, weak object signals, and small object scales make accurate detection particularly challenging.<n>A common strategy is to integrate single-image super-resolution (SR) before detection.<n>We propose a Saliency-Driven multi-task Collaborative Network (SDCoNet) that couples SR and detection through implicit feature sharing.
  arXiv  Detail & Related papers  (2026-01-18T17:36:48Z)
• Learning Object-Centric Representations in SAR Images with Multi-Level Feature Fusion [5.295349411568878]
  SlotSAR disentangles target representations from background clutter in SAR images without mask annotations.<n>We present a multi-level slot attention module that integrates these low- and high-level features to enhance slot-wise representation distinctiveness.
  arXiv  Detail & Related papers  (2025-09-11T09:42:32Z)
• Attention-Based Fusion of IQ and FFT Spectrograms with AoA Features for GNSS Jammer Localization [4.674584508653125]
  Jamming devices disrupt signals from the global navigation satellite system (GNSS)<n>Classical Angle of Arrival (AoA) methods exhibit reduced accuracy in multipath environments.<n>We propose a novel approach for detecting and classifying interference while estimating the distance, azimuth, and elevation of jamming sources.
  arXiv  Detail & Related papers  (2025-07-09T06:49:11Z)
• 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. 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. 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)
• RSNet: A Light Framework for The Detection of Multi-scale Remote Sensing Targets [10.748210940033484]
  RSNet is a lightweight framework to enhance ship detection in SAR imagery. Waveletpool-ContextGuided (WCG) is the backbone, guiding global context understanding. Waveletpool-StarFusion (WSF) is introduced as the neck, employing a residual wavelet element-wise multiplication structure.
  arXiv  Detail & Related papers  (2024-10-30T14:46:35Z)
• Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery [51.83786195178233]
  We design a Knowledge Discovery Network (KDN) to implement the renormalization group theory in terms of efficient feature extraction. Renormalized connection (RC) on the KDN enables synergistic focusing'' of multi-scale features. RCs extend the multi-level feature's divide-and-conquer'' mechanism of the FPN-based detectors to a wide range of scale-preferred tasks.
  arXiv  Detail & Related papers  (2024-09-09T13:56:22Z)
• A Real-time Faint Space Debris Detector With Learning-based LCM [4.454216126942097]
  This paper proposes a method for low-SNR streak extraction based on local contrast and maximum likelihood estimation (MLE) The algorithm in this paper is of high speed and precision, which guarantees its promising applications in the extraction of high dynamic targets.
  arXiv  Detail & Related papers  (2023-09-15T08:37:28Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization [81.29406957201458]
  Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection. We propose to model the rotated objects as Gaussian distributions. We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation.
  arXiv  Detail & Related papers  (2022-09-22T07:50:48Z)
• SAR-ShipNet: SAR-Ship Detection Neural Network via Bidirectional Coordinate Attention and Multi-resolution Feature Fusion [7.323279438948967]
  This paper studies a practically meaningful ship detection problem from synthetic aperture radar (SAR) images by the neural network. We propose a SAR-ship detection neural network (call SAR-ShipNet for short), by newly developing Bidirectional Coordinate Attention (BCA) and Multi-resolution Feature Fusion (MRF) based on CenterNet. Experimental results on the public SAR-Ship dataset show that our SAR-ShipNet achieves competitive advantages in both speed and accuracy.
  arXiv  Detail & Related papers  (2022-03-29T12:27:04Z)
• 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)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Learning Efficient Representations for Enhanced Object Detection on Large-scene SAR Images [16.602738933183865]
  It is a challenging problem to detect and recognize targets on complex large-scene Synthetic Aperture Radar (SAR) images. Recently developed deep learning algorithms can automatically learn the intrinsic features of SAR images. We propose an efficient and robust deep learning based target detection method.
  arXiv  Detail & Related papers  (2022-01-22T03:25:24Z)
• MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images [51.227489316673484]
  We propose an arbitrary-oriented region proposal network (AO-RPN) to generate oriented proposals transformed from horizontal anchors. To obtain accurate bounding boxes, we decouple the detection task into multiple subtasks and propose a multi-head network. Each head is specially designed to learn the features optimal for the corresponding task, which allows our network to detect objects accurately.
  arXiv  Detail & Related papers  (2020-12-24T06:36:48Z)

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.