中文
相关论文

相关论文: PGTRNet: Two-phase Weakly Supervised Object Detect…

200 篇论文

Deep learning-based image restoration has achieved significant success. However, when addressing real-world degradations, model performance is limited by the quality of groundtruth images in datasets due to practical constraints in data…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Donghun Ryou , Inju Ha , Sanghyeok Chu , Bohyung Han

Many recently developed object detectors focused on coarse-to-fine framework which contains several stages that classify and regress proposals from coarse-grain to fine-grain, and obtains more accurate detection gradually. Multi-resolution…

计算机视觉与模式识别 · 计算机科学 2020-03-11 Li Xiao , Yufan Luo , Chunlong Luo , Lianhe Zhao , Quanshui Fu , Guoqing Yang , Anpeng Huang , Yi Zhao

Object detection using single point supervision has received increasing attention over the years. However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large. In this…

计算机视觉与模式识别 · 计算机科学 2022-10-21 Pengfei Chen , Xuehui Yu , Xumeng Han , Najmul Hassan , Kai Wang , Jiachen Li , Jian Zhao , Humphrey Shi , Zhenjun Han , Qixiang Ye

Object detection has been vigorously investigated for years but fast accurate detection for real-world scenes remains a very challenging problem. Overcoming drawbacks of single-stage detectors, we take aim at precisely detecting objects for…

计算机视觉与模式识别 · 计算机科学 2020-03-16 Xingyu Chen , Junzhi Yu , Shihan Kong , Zhengxing Wu , Li Wen

Ground Penetrating Radar (GPR) is one of the most important non-destructive evaluation (NDE) devices to detect the subsurface objects (i.e. rebars, utility pipes) and reveal the underground scene. One of the biggest challenges in GPR based…

信号处理 · 电气工程与系统科学 2020-08-21 Jinglun Feng , Liang Yang , Haiyan Wang , Yifeng Song , Jizhong Xiao

Recent salient object detection (SOD) models predominantly rely on heavyweight backbones, incurring substantial computational cost and hindering their practical application in various real-world settings, particularly on edge devices. This…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Yu-Huan Wu , Wei Liu , Zi-Xuan Zhu , Zizhou Wang , Yong Liu , Liangli Zhen

The emergence of deepfake technology has introduced a range of societal problems, garnering considerable attention. Current deepfake detection methods perform well on specific datasets, but exhibit poor performance when applied to datasets…

计算机视觉与模式识别 · 计算机科学 2025-08-15 Lixin Jia , Zhiqing Guo , Gaobo Yang , Liejun Wang , Keqin Li

We study on weakly-supervised object detection (WSOD) which plays a vital role in relieving human involvement from object-level annotations. Predominant works integrate region proposal mechanisms with convolutional neural networks (CNN).…

计算机视觉与模式识别 · 计算机科学 2019-09-12 Zhaoyang Zeng , Bei Liu , Jianlong Fu , Hongyang Chao , Lei Zhang

Ground penetrating radar (GPR) has become a rapid and non-destructive solution for road subsurface distress (RSD) detection. However, recognizing RSD from GPR images is labor-intensive and heavily relies on the expertise of inspectors. Deep…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Chang Peng , Bao Yang , Meiqi Li , Ge Zhang , Hui Sun , Zhenyu Jiang

Semi-supervised object detection (SSOD) is a research hot spot in computer vision, which can greatly reduce the requirement for expensive bounding-box annotations. Despite great success, existing progress mainly focuses on two-stage…

计算机视觉与模式识别 · 计算机科学 2023-02-23 Gen Luo , Yiyi Zhou , Lei Jin , Xiaoshuai Sun , Rongrong Ji

In low-altitude surveillance and early warning systems, detecting weak moving targets remains a significant challenge due to low signal energy, small spatial extent, and complex background clutter. Existing methods struggle with extracting…

计算机视觉与模式识别 · 计算机科学 2025-07-24 Weihua Gao , Chunxu Ren , Wenlong Niu , Xiaodong Peng

Training object detectors with only image-level annotations is very challenging because the target objects are often surrounded by a large number of background clutters. Many existing approaches tackle this problem through object proposal…

计算机视觉与模式识别 · 计算机科学 2017-08-08 Wenhui Jiang , Thuyen Ngo , B. S. Manjunath , Zhicheng Zhao , Fei Su

Weakly-Supervised Camouflaged Object Detection (WSCOD) has gained popularity for its promise to train models with weak labels to segment objects that visually blend into their surroundings. Recently, some methods using sparsely-annotated…

计算机视觉与模式识别 · 计算机科学 2025-01-13 Tsui Qin Mok , Shuyong Gao , Haozhe Xing , Miaoyang He , Yan Wang , Wenqiang Zhang

The core challenge in Camouflage Object Detection (COD) lies in the indistinguishable similarity between targets and backgrounds in terms of color, texture, and shape. This causes existing methods to either lose edge details (such as…

计算机视觉与模式识别 · 计算机科学 2025-05-15 Jianlin Sun , Xiaolin Fang , Juwei Guan , Dongdong Gui , Teqi Wang , Tongxin Zhu

Traditional ground-penetrating radar (GPR) data inversion leverages iterative algorithms which suffer from high computation costs and low accuracy when applied to complex subsurface scenarios. Existing deep learning-based methods focus on…

信号处理 · 电气工程与系统科学 2022-09-21 Qiqi Dai , Yee Hui Lee , Hai-Han Sun , Genevieve Ow , Mohamed Lokman Mohd Yusof , Abdulkadir C. Yucel

Weakly supervised semantic segmentation (WSSS), a fundamental computer vision task, which aims to segment out the object within only class-level labels. The traditional methods adopt the CNN-based network and utilize the class activation…

计算机视觉与模式识别 · 计算机科学 2023-10-03 Jingliang Deng , Zonghan Li

Detecting camouflaged objects in underwater environments is crucial for marine ecological research and resource exploration. However, existing methods face two key challenges: underwater image degradation, including low contrast and color…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Xinxin Huang , Han Sun , Junmin Cai , Ningzhong Liu , Huiyu Zhou

Weakly supervised semantic segmentation and localiza- tion have a problem of focusing only on the most important parts of an image since they use only image-level annota- tions. In this paper, we solve this problem fundamentally via…

计算机视觉与模式识别 · 计算机科学 2017-08-17 Dahun Kim , Donghyeon Cho , Donggeun Yoo , In So Kweon

The aim of surface defect detection is to identify and localise abnormal regions on the surfaces of captured objects, a task that's increasingly demanded across various industries. Current approaches frequently fail to fulfil the extensive…

计算机视觉与模式识别 · 计算机科学 2024-08-23 Blaž Rolih , Matic Fučka , Danijel Skočaj

Camouflaged object detection (COD) from a single image is a challenging task due to the high similarity between objects and their surroundings. Existing fully supervised methods require labor-intensive pixel-level annotations, making weakly…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Xia Li , Xinran Liu , Lin Qi , Junyu Dong