Filters








256,196 Hits in 3.1 sec

Cross-Supervised Object Detection [article]

Zitian Chen, Zhiqiang Shen, Jiahui Yu, Erik Learned-Miller
2020 arXiv   pre-print
We call this novel learning paradigm cross-supervised object detection.  ...  These contributions enable us to better detect novel objects with image-level annotations in complex multi-object scenes such as the COCO dataset.  ...  CONCLUSION We focus on a novel learning paradigm-cross-supervised object detection.  ... 
arXiv:2006.15056v2 fatcat:l6oduwrabnhfbafbddub5nzhri

CLASS: Cross-Level Attention and Supervision for Salient Objects Detection [article]

Lv Tang, Bo Li
2020 arXiv   pre-print
Second, a novel cross-level supervision (CLS) is designed to learn complementary context for complex structures through pixel-level, region-level and object-level.  ...  Salient object detection (SOD) is a fundamental computer vision task. Recently, with the revival of deep neural networks, SOD has made great progresses.  ...  cross-level attention module and cross-level supervision respectively.  ... 
arXiv:2009.10916v2 fatcat:mo2tjhckcfhp5h253bucdnijhq

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning [article]

Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Tong Shen, Pei Yu, Dimitrios Lymberopoulos, Sidi Lu, Weisong Shi, Xiang Chen
2021 arXiv   pre-print
To enable SSL for cross-domain object detection, we propose fine-grained domain transfer, progressive-confidence-based label sharpening and imbalanced sampling strategy to address two challenges: (i) non-identical  ...  To overcome this limitation, we propose the Cross-Domain Semi-Supervised Learning (CDSSL) framework by leveraging high-quality pseudo labels to learn better representations from the target domain directly  ...  ., different object density distribution) which are important for object detections. Semi-Supervised Learning.  ... 
arXiv:1911.07158v5 fatcat:avo3zydua5dalo7e6ggnik3wuy

RODNet: Radar Object Detection Using Cross-Modal Supervision [article]

Yizhou Wang, Zhongyu Jiang, Xiangyu Gao, Jenq-Neng Hwang, Guanbin Xing, Hui Liu
2021 arXiv   pre-print
In this paper, we propose a deep radar object detection network (RODNet), to effectively detect objects purely from the carefully processed radar frequency data in the format of range-azimuth frequency  ...  After intensive experiments, our RODNet shows favorable object detection performance without the presence of the camera.  ...  In this paper, we propose a radar object detection method, cross-supervised by a camera-radar fusion algorithm, that can accurately detect objects purely with the radar signal input.  ... 
arXiv:2003.01816v2 fatcat:rrmg45oglzcyboiee7llg64vda

CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection [article]

Ye Guo, Yali Li, Shengjin Wang
2020 arXiv   pre-print
In this paper, we present a novel cross-supervised learning pipeline for large-scale object detection, denoted as CS-R-FCN.  ...  First, we propose to utilize the data flow of image-level annotated images in the fully-supervised two-stage object detection framework, leading to cross-supervised learning combining bounding-box-level  ...  a more powerful validation for cross-supervised object detection task.  ... 
arXiv:1905.12863v2 fatcat:7niianelejashfi57n775w6wvu

Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [article]

Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, Kiyoharu Aizawa
2018 arXiv   pre-print
In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question.  ...  Can we detect common objects in a variety of image domains without instance-level annotations?  ...  We tackle a novel task, cross-domain weakly supervised object detection.  ... 
arXiv:1803.11365v1 fatcat:54p7yqkf6fcrhdqnadcwn2gcma

Semi-Supervised Cross-Modal Salient Object Detection with U-Structure Networks [article]

Yunqing Bao, Hang Dai, Abdulmotaleb Elsaddik
2022 arXiv   pre-print
Salient Object Detection (SOD) is a popular and important topic aimed at precise detection and segmentation of the interesting regions in the images.  ...  We integrate the linguistic information into the vision-based U-Structure networks designed for salient object detection tasks.  ...  This also makes our entire training process semi-supervised. Then we have DUT-OMRON Cross Modal (DUT-OMRON-CM) and HKU-IS Cross Modal (HKU-IS-CM).  ... 
arXiv:2208.04361v1 fatcat:6bbaznm7lras7dzt6wmz3inpdq

Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation

Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, Kiyoharu Aizawa
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question.  ...  Can we detect common objects in a variety of image domains without instance-level annotations?  ...  We tackle a novel task, cross-domain weakly supervised object detection.  ... 
doi:10.1109/cvpr.2018.00525 dblp:conf/cvpr/InoueFYA18 fatcat:g66l47zivbgl7li3p373pe5jxa

RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization [article]

Yizhou Wang, Zhongyu Jiang, Yudong Li, Jenq-Neng Hwang, Guanbin Xing, Hui Liu
2021 arXiv   pre-print
In this paper, we propose a deep radar object detection network, named RODNet, which is cross-supervised by a camera-radar fused algorithm without laborious annotation efforts, to effectively detect objects  ...  With intensive experiments, our proposed cross-supervised RODNet achieves 86% average precision and 88% average recall of object detection performance, which shows the robustness to noisy scenarios in  ...  In this paper, we propose a radar object detection method, cross-supervised by a camera-radar fusion algorithm in the training stage, that can accurately detect objects purely based on the radar signals  ... 
arXiv:2102.05150v1 fatcat:pryve6rlfbetzkph7gz47sfqzy

Multi-perspective cross-class domain adaptation for open logo detection

Hang Su, Shaogang Gong, Xiatian Zhu
2020 Computer Vision and Image Understanding  
To generalise and transfer knowledge of fully supervised logo classes to other 1-shot icon supervised classes, we propose a Multi-Perspective Cross-Class (MPCC) domain adaptation method.  ...  Existing logo detection methods mostly rely on supervised learning with a large quantity of labelled training data in limited classes.  ...  Both methods aim to address the cross-class detection challenge by training data synthesis.  ... 
doi:10.1016/j.cviu.2020.103156 fatcat:o42uzsff2rd4rkpjurvugcpn6a

Weakly Supervised Cross-domain Mixed Dish Detection with Mean-teacher

Lixi Deng, Xu Zhang, Zhijie Shang
2020 IEEE Access  
Cross-domain object detection Our work is also related to cross-domain object detection.  ...  the weakly supervised object detection by using image-level annotations to localize objects.  ... 
doi:10.1109/access.2020.3035715 fatcat:itcaxygsqzbatndfbokknu77oa

Sparse-shot Learning with Exclusive Cross-Entropy for Extremely Many Localisations [article]

Andreas Panteli, Jonas Teuwen, Hugo Horlings, Efstratios Gavves
2021 arXiv   pre-print
Experiments on nine datasets and two different localisation tasks, detection with YOLLO and segmentation with Unet, show that we obtain considerable improvements compared to cross-entropy or focal loss  ...  Object localisation, in the context of regular images, often depicts objects like people or cars.  ...  Exclusive cross-entropy correctly detects most objects while avoiding erroneous background predictions.  ... 
arXiv:2104.10425v2 fatcat:oitlv4tozbghdi4p6oyzv4caai

Weakly Supervised 3D Object Detection from Point Clouds [article]

Zengyi Qin, Jinglu Wang, Yan Lu
2020 arXiv   pre-print
Weakly supervised learning is a promising approach to reducing the annotation requirement, but existing weakly supervised object detectors are mostly for 2D detection rather than 3D.  ...  The source code and pretrained models are publicly available at https://github.com/Zengyi-Qin/Weakly-Supervised-3D-Object-Detection.  ...  VS3D and fully supervised methods in 3D object detection.  ... 
arXiv:2007.13970v1 fatcat:2n6irzxxh5cj7mjckign3knlsq

Weakly Supervised Video Salient Object Detection via Point Supervision [article]

Shuyong Gao, Haozhe Xing, Wei Zhang, Yan Wang, Qianyu Guo, Wenqiang Zhang
2022 arXiv   pre-print
Video salient object detection models trained on pixel-wise dense annotation have achieved excellent performance, yet obtaining pixel-by-pixel annotated datasets is laborious.  ...  To exploit long-term cues, we develop the Long-term Cross-Frame Attention module (LCFA), which assists the current frame in inferring salient objects based on multi-frame tokens.  ...  Both fully supervised and weakly supervised salient object detection methods have achieved large advances.  ... 
arXiv:2207.07269v1 fatcat:6qb3t6nkm5aktonkb7wot4d72q

AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection [article]

Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinghong Jiang, Feng Zhao, Bolei Zhou, Hang Zhao
2022 arXiv   pre-print
In this paper, we propose AutoAlign, an automatic feature fusion strategy for 3D object detection.  ...  Object detection through either RGB images or the LiDAR point clouds has been extensively explored in autonomous driving.  ...  . 3D Object Detection with Multi-modalities Recently, multi-modal fusion for object detection attracts numerous attentions.  ... 
arXiv:2201.06493v2 fatcat:tn5nyt3m4vcdvemhsjom253lkq
« Previous Showing results 1 — 15 out of 256,196 results