# You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection

arXiv: https://arxiv.org/abs/2504.15694 · HTML: https://mlsanity.com/paper/2504.15694/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Builds on (most cited first, 18 of 18)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer](https://mlsanity.com/paper/2407.17140/) (2024)
- [Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration](https://mlsanity.com/paper/2311.16845/) (2023)
- [Anomaly Detection in Autonomous Driving: A Survey](https://mlsanity.com/paper/2204.07974/) (2022)
- [A Dataset And Benchmark Of Underwater Object Detection For Robot Picking](https://mlsanity.com/paper/2106.05681/) (2021)
- [MF-MOS: A Motion-Focused Model for Moving Object Segmentation](https://mlsanity.com/paper/2401.17023/) (2024)
- [DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimation](https://mlsanity.com/paper/2405.16960/) (2024)
- [Is Underwater Image Enhancement All Object Detectors Need?](https://mlsanity.com/paper/2311.18814/) (2023)
- [ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction](https://mlsanity.com/paper/2412.11210/) (2024)
- [CPOT: Channel Pruning via Optimal Transport](https://mlsanity.com/paper/2005.10451/) (2020)
- [These Maps Are Made by Propagation: Adapting Deep Stereo Networks to Road Scenarios with Decisive Disparity Diffusion](https://mlsanity.com/paper/2411.03717/) (2024)
- [A Real-Time Framework for Domain-Adaptive Underwater Object Detection with Image Enhancement](https://mlsanity.com/paper/2403.19079/) (2024)
- [Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaboration](https://mlsanity.com/paper/2412.03055/) (2024)

## Built on by (most cited first, 2 of 2)

- [Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation](https://mlsanity.com/paper/2506.23505/) (2025)
- [FMRFusion: Frequency-Aware Multi-View Representation Learning for Heterogeneous Image Fusion](https://mlsanity.com/paper/2606.07985/) (2026)

## Abstract (arXiv)

Despite the remarkable achievements in object detection, the model's accuracy and efficiency still require further improvement under challenging underwater conditions, such as low image quality and limited computational resources. To address this, we propose an Ultra-Light Real-Time Underwater Object Detection framework, You Sense Only Once Beneath (YSOOB). Specifically, we utilize a Multi-Spectrum Wavelet Encoder (MSWE) to perform frequency-domain encoding on the input image, minimizing the semantic loss caused by underwater optical color distortion. Furthermore, we revisit the unique characteristics of even-sized and transposed convolutions, allowing the model to dynamically select and enhance key information during the resampling process, thereby improving its generalization ability. Finally, we eliminate model redundancy through a simple yet effective channel compression and reconstructed large kernel convolution (RLKC) to achieve model lightweight. As a result, forms a high-performance underwater object detector YSOOB with only 1.2 million parameters. Extensive experimental results demonstrate that, with the fewest parameters, YSOOB achieves mAP50 of 83.1% and 82.9% on the URPC2020 and DUO datasets, respectively, comparable to the current SOTA detectors. The inference speed reaches 781.3 FPS and 57.8 FPS on the T4 GPU (TensorRT FP16) and the edge computing device Jetson Xavier NX (TensorRT FP16), surpassing YOLOv12-N by 28.1% and 22.5%, respectively.