FinSight-Net:A Physics-Aware Decoupled Network with Frequency-Domain Compensation for Underwater Fish Detection in Smart Aquaculture

• URL: http://arxiv.org/abs/2602.19437v1
• Date: Mon, 23 Feb 2026 02:12:47 GMT
• Title: FinSight-Net:A Physics-Aware Decoupled Network with Frequency-Domain Compensation for Underwater Fish Detection in Smart Aquaculture
• Authors: Jinsong Yang, Zeyuan Hu, Yichen Li, Hong Yu,
• Abstract summary: FinSight-Net is an efficient and physics-aware fish detection framework for aquaculture environments.<n>We show that FinSight-Net reaches 92.8% mAP, outperforming YOLOv11s by 4.8% while reducing parameters by 29.0%.<n>In particular, on UW-BlurredFish, FinSight-Net reaches 92.8% mAP, outperforming YOLOv11s by 4.8% while reducing parameters by 29.0%.
• Score: 8.150520348578087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Underwater fish detection (UFD) is a core capability for smart aquaculture and marine ecological monitoring. While recent detectors improve accuracy by stacking feature extractors or introducing heavy attention modules, they often incur substantial computational overhead and, more importantly, neglect the physics that fundamentally limits UFD: wavelength-dependent absorption and turbidity-induced scattering significantly degrade contrast, blur fine structures, and introduce backscattering noise, leading to unreliable localization and recognition. To address these challenges, we propose FinSight-Net, an efficient and physics-aware detection framework tailored for complex aquaculture environments. FinSight-Net introduces a Multi-Scale Decoupled Dual-Stream Processing (MS-DDSP) bottleneck that explicitly targets frequency-specific information loss via heterogeneous convolutional branches, suppressing backscattering artifacts while compensating distorted biological cues through scale-aware and channel-weighted pathways. We further design an Efficient Path Aggregation FPN (EPA-FPN) as a detail-filling mechanism: it restores high-frequency spatial information typically attenuated in deep layers by establishing long-range skip connections and pruning redundant fusion routes, enabling robust detection of non-rigid fish targets under severe blur and turbidity. Extensive experiments on DeepFish, AquaFishSet, and our challenging UW-BlurredFish benchmark demonstrate that FinSight-Net achieves state-of-the-art performance. In particular, on UW-BlurredFish, FinSight-Net reaches 92.8% mAP, outperforming YOLOv11s by 4.8% while reducing parameters by 29.0%, providing a strong and lightweight solution for real-time automated monitoring in smart aquaculture.

Related papers

• SPMamba-YOLO: An Underwater Object Detection Network Based on Multi-Scale Feature Enhancement and Global Context Modeling [12.390389688362506]
  We propose a novel underwater object detection network that integrates multi-scale feature enhancement with global context modeling.<n>Experiments on the URPC2022 dataset demonstrate that the network outperforms the YOLOv8n baseline by more than 4.9% in mAP@0.5.
  arXiv  Detail & Related papers  (2026-02-26T06:45:11Z)
• PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement [63.007237197267834]
  Existing deep learning methods are mostly physiological monitoring and lack theoretical robustness.<n>We propose a physics-informed r paradigm derived from the Navier-Stokes equations of hemodynamics, showing that the pulse signal follows a second-order system.<n>This provides a theoretical justification for using a Temporal Conal Network (TCN)<n>Phase-Net achieves state-of-the-art performance with strong efficiency, offering a theoretically grounded and deployment-ready r solution.
  arXiv  Detail & Related papers  (2025-09-29T14:36:45Z)
• Data-Driven Reconstruction of Significant Wave Heights from Sparse Observations [3.356199201143573]
  We introduce AUWave, a hybrid deep learning framework that fuses a station-wise sequence encoder (MLP) with a multi-scale U-Net.<n>We show that AUWave consistently outperforms a representative baseline in data-richer configurations.<n>The architecture's multi-scale and attention components translate into accuracy gains when minimal but non-trivial spatial anchoring is available.
  arXiv  Detail & Related papers  (2025-09-21T14:12:28Z)
• OASIS: Harnessing Diffusion Adversarial Network for Ocean Salinity Imputation using Sparse Drifter Trajectories [55.860116803220535]
  Ocean salinity plays a vital role in circulation, climate, and marine ecosystems, yet its measurement is often sparse, irregular, and noisy.<n>Traditional approaches rely on linearity and stationarity, and are limited by cloud cover, sensor drift, and low satellite revisit rates.<n>We introduce the OceAn Salinity Imputation System (OASIS), a novel diffusion adversarial framework designed to address these challenges.
  arXiv  Detail & Related papers  (2025-08-29T12:25:26Z)
• EPANet: Efficient Path Aggregation Network for Underwater Fish Detection [6.6069949373696994]
  We propose an efficient path aggregation network (EPANet) for underwater fish detection (UFD)<n>EPANet consists of two key components: an efficient path aggregation feature pyramid network (EPA-FPN) and a multi-scale diverse-division short path bottleneck (MS-DDSP bottleneck)<n> experiments on benchmark UFD datasets demonstrate that EPANet outperforms state-of-the-art methods in terms of detection accuracy and inference speed.
  arXiv  Detail & Related papers  (2025-08-01T11:09:13Z)
• Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation [0.20767168898581637]
  Underwater object detection is crucial for autonomous navigation, environmental monitoring, and marine exploration.<n>Current methods balance accuracy and computational efficiency, but they have trouble deploying in real-time under low visibility conditions.<n>This study advances underwater detection through the integration of physics-informed augmentation techniques with the YOLOv12 architecture.
  arXiv  Detail & Related papers  (2025-06-30T04:06:50Z)
• SU-YOLO: Spiking Neural Network for Efficient Underwater Object Detection [15.935285733525962]
  Spiking Underwater YOLO (SU-YOLO) is a Spiking Neural Network (SNN) model for underwater object detection.<n>SU-YOLO incorporates a novel spike-based underwater image denoising method based solely on integer addition.<n>Results demonstrate that SU-YOLO achieves mAP of 78.8% with 6.97M parameters and an energy consumption of 2.98 mJ.
  arXiv  Detail & Related papers  (2025-03-31T17:59:52Z)
• Frequency Domain Enhanced U-Net for Low-Frequency Information-Rich Image Segmentation in Surgical and Deep-Sea Exploration Robots [34.28684917337352]
  We address the differences in frequency band sensitivity between CNNs and the human visual system.<n>We propose a wavelet adaptive spectrum fusion (WASF) method inspired by biological vision mechanisms to balance cross-frequency image features.<n>We develop the FE-UNet model, which employs a SAM2 backbone network and incorporates fine-tuned Hiera-Large modules to ensure segmentation accuracy.
  arXiv  Detail & Related papers  (2025-02-06T07:24:34Z)
• Learning Heavily-Degraded Prior for Underwater Object Detection [59.5084433933765]
  This paper seeks transferable prior knowledge from detector-friendly images. It is based on statistical observations that, the heavily degraded regions of detector-friendly (DFUI) and underwater images have evident feature distribution gaps. Our method with higher speeds and less parameters still performs better than transformer-based detectors.
  arXiv  Detail & Related papers  (2023-08-24T12:32:46Z)
• Efficient Real-time Smoke Filtration with 3D LiDAR for Search and Rescue with Autonomous Heterogeneous Robotic Systems [56.838297900091426]
  Smoke and dust affect the performance of any mobile robotic platform due to their reliance on onboard perception systems. This paper proposes a novel modular computation filtration pipeline based on intensity and spatial information.
  arXiv  Detail & Related papers  (2023-08-14T16:48:57Z)
• DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation [44.99833362998488]
  We present DeepAqua, a self-supervised deep learning model that eliminates the need for manual annotations during the training phase. We exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. Experimental results show that DeepAqua outperforms other unsupervised methods by improving accuracy by 7%, Intersection Over Union by 27%, and F1 score by 14%.
  arXiv  Detail & Related papers  (2023-05-02T18:06:21Z)
• Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images [193.77450545067967]
  We propose an end-to-end Dense Attention Fluid Network (DAFNet) for salient object detection in optical remote sensing images (RSIs) A Global Context-aware Attention (GCA) module is proposed to adaptively capture long-range semantic context relationships. We construct a new and challenging optical RSI dataset for SOD that contains 2,000 images with pixel-wise saliency annotations.
  arXiv  Detail & Related papers  (2020-11-26T06:14:10Z)
• A water-obstacle separation and refinement network for unmanned surface vehicles [13.515085879331425]
  We propose a new deep encoder-decoder architecture, a water-obstacle separation and refinement network (WaSR) to address these issues. We show that WaSR outperforms the current state-of-the-art by a large margin, yielding a 14% increase in F-measure over the second-best method.
  arXiv  Detail & Related papers  (2020-01-07T07:47:52Z)

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.