Prior-Guided Dual-Reference Contrastive Learning for Underwater Object Detection

计算机科学 人工智能 目标检测 计算机视觉 水下 对象(语法) 对偶(语法数字) 模式识别(心理学) 艺术 海洋学 文学类 地质学
作者
Lei Cao,Liquan Shen,Yu Meng,Zhengyong Wang,Cheng Shen
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:35 (8): 8209-8224 被引量:12
标识
DOI:10.1109/tcsvt.2025.3545694
摘要

Underwater object detection (UOD) plays an important role in the exploitation of marine ecological resources. Different from terrestrial images, the complex underwater environment leads to significant degradation in underwater images, which brings great difficulty in accurate object detection. In recent years, many specially designed UOD methods have been proposed to improve the detection precision in two aspects based on underwater image characteristics: 1) Some UOD methods utilize underwater image enhancement (UIE) to alleviate degradation with the expectation of clean features. However, neither preprocessing nor cascade approaches are fully effective for detection-oriented enhancement, while the additional UIE network increases inference time. 2) Other UOD methods consider low visibility of objects, blurriness of small objects, and occlusion problems. However, the semantic complementarity between objects of the same category but different qualities and the background patterns of specific objects are ignored. Based on these two observations, we propose a novel framework for the UOD task, which performs feature enhancement in two ways. First, a group contrastive-based feature enhancement module (GCFEM) is proposed to bridge UIE and UOD. Specifically, multiple enhanced versions by UIEs are evaluated by the object detection precision evaluation pipeline. Then, group-based contrastive learning is introduced, which utilizes multiple groups of enhanced versions to guide the backbone in extracting detection-friendly features. Second, a prior-guided dual-reference feature enhancement module (PDFEM) is proposed to enhance the representation of objects further. Specifically, the explicit object-object relationship allows low-quality object regions to refer to high-quality ones, guided by a transmission map. At the same time, the implicit object-background relationship provides cues about the surroundings for the representation of the objects. Experimental results demonstrate that the proposed algorithm outperforms many state-of-the-art UOD methods on RUOD and URPC2020 datasets.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
zhangyupei的应助被跳跃的南琴采纳,获得10
1秒前
可若好烦完成签到,获得积分10
1秒前
orixero的应助被zyux采纳,获得10
1秒前
三文鱼发布了新的文献求助10
2秒前
zz发布了新的文献求助10
2秒前
科目三的应助被Vivian采纳,获得10
2秒前
2秒前
Ava的应助被活泼啤酒采纳,获得10
3秒前
3秒前
xinxin发布了新的文献求助10
4秒前
刘璐完成签到 ,获得积分10
4秒前
Wdw2236发布了新的文献求助10
4秒前
搜集达人的应助被研友_LNVX1L采纳,获得10
4秒前
5秒前
5秒前
slin_sjtu完成签到,获得积分0
6秒前
null的应助被可若好烦采纳,获得10
7秒前
lyn完成签到 ,获得积分10
7秒前
wg发布了新的文献求助10
8秒前
马颗粒发布了新的文献求助30
8秒前
SciGPT的应助被王亚奇采纳,获得10
9秒前
9秒前
9秒前
王晨发布了新的文献求助10
10秒前
烨采发布了新的文献求助10
11秒前
跳跃的南琴完成签到,获得积分10
11秒前
liumu发布了新的文献求助10
11秒前
复杂的海冬完成签到,获得积分10
12秒前
我不是驴熊完成签到,获得积分10
12秒前
传奇3的应助被明日秋风采纳,获得10
13秒前
13秒前
不是老羊完成签到,获得积分10
14秒前
活泼啤酒发布了新的文献求助10
14秒前
wjwless完成签到,获得积分10
14秒前
RobiN发布了新的文献求助10
15秒前
15秒前
852的应助被第一作者采纳,获得10
15秒前
研友_ZragOn发布了新的文献求助10
16秒前
少少少发布了新的文献求助10
16秒前
Cdvsd完成签到 ,获得积分10
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8188088
求助须知:如何正确求助?哪些是违规求助? 9575942
关于积分的说明 21844291
捐赠科研通 7785857
什么是DOI,文献DOI怎么找? 3435158
关于科研通互助平台的介绍 2559529
邀请新用户注册赠送积分活动 2482065