Filters








154 Hits in 6.7 sec

Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images [article]

Zhou Huang, Tian-Zhu Xiang, Huai-Xin Chen, Hang Dai
2022 arXiv   pre-print
Then, the boundary semantics are integrated with high-level features to guide the salient object detection under the supervision of scribble labels.  ...  To this end, in this paper, we propose a novel weakly-supervised salient object detection framework to predict the saliency of remote sensing images from sparse scribble annotations.  ...  We find that the boundary/edge cue is very beneficial for weakly-supervised salient object detection.  ... 
arXiv:2202.03501v1 fatcat:e6goup4pdbcjfag56nyqw4y5v4

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TIP 2021 1882-1897 Data mining Bifurcated Backbone Strategy for RGB-D Salient Object Detection.  ...  ., +, TIP 2021 5559-5572 Computer architecture Dynamic Selective Network for RGB-D Salient Object Detection.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

2020 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 42

2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Online Meta Adaptation for Fast Video Object Segmentation. Xiao, H., +, TPAMI May 2020 1205-1217 PCL: Proposal Cluster Learning for Weakly Supervised Object Detection.  ...  ., +, TPAMI Oct. 2020 2333-2345 Joint Task-Recursive Learning for RGB-D Scene Understanding.  ...  ., +, TPAMI May 2020 1272-1278 PCL: Proposal Cluster Learning for Weakly Supervised Object Detection.  ... 
doi:10.1109/tpami.2020.3036557 fatcat:3j6s2l53x5eqxnlsptsgbjeebe

Generative Transformer for Accurate and Reliable Salient Object Detection [article]

Yuxin Mao, Jing Zhang, Zhexiong Wan, Yuchao Dai, Aixuan Li, Yunqiu Lv, Xinyu Tian, Deng-Ping Fan, Nick Barnes
2022 arXiv   pre-print
We apply the proposed inferential generative adversarial network (iGAN) to both fully and weakly supervised salient object detection, and explain that iGAN within the transformer framework leads to both  ...  accurate and reliable salient object detection.  ...  for large salient object detection.  ... 
arXiv:2104.10127v4 fatcat:yaunhucuvbba3bvp3iatzdnnxa

Associating Inter-image Salient Instances for Weakly Supervised Semantic Segmentation [chapter]

Ruochen Fan, Qibin Hou, Ming-Ming Cheng, Gang Yu, Ralph R. Martin, Shi-Min Hu
2018 Lecture Notes in Computer Science  
In this paper, we use an instance-level salient object detector to automatically generate salient instances (candidate objects) for training images.  ...  When working with DeepLab for semantic segmentation, our method outperforms state-of-the-art weakly supervised alternatives by a large margin, achieving 65.6% mIoU on the PASCAL VOC 2012 dataset.  ...  ), the national youth talent support program, Tianjin Natural Science Foundation for Distinguished Young Scholars (NO. 17JCJQJC43700), Huawei Innovation Research Program.  ... 
doi:10.1007/978-3-030-01240-3_23 fatcat:cl46tczynff2tdx2myeprmjvhq

Cascade Graph Neural Networks for RGB-D Salient Object Detection [article]

Ao Luo, Xin Li, Fan Yang, Zhicheng Jiao, Hong Cheng, Siwei Lyu
2020 arXiv   pre-print
In this paper, we study the problem of salient object detection (SOD) for RGB-D images using both color and depth information.A major technical challenge in performing salient object detection fromRGB-D  ...  the mutual benefits between these two data sources through a set of cascade graphs, to learn powerful representations for RGB-D salient object detection.  ...  Introduction Salient object detection is the crux to dozens of high-level AI tasks such as object detection or classification [53, 81, 70] , weakly-supervised semantic segmentation [31, 64] , semantic  ... 
arXiv:2008.03087v1 fatcat:nrjn4fkk65bynf3yyzfjn4wimy

Weakly Supervised Learning for Salient Object Detection [article]

Huaizu Jiang
2015 arXiv   pre-print
To avoid the requirement of expensive pixel-wise salient region annotations, in this paper, we study weakly supervised learning approaches for salient object detection.  ...  Recent advances in supervised salient object detection has resulted in significant performance on benchmark datasets.  ...  Weakly Supervised Salient Object Detection In this section, we first present a weakly supervised approach for salient object detection based on the latent structural SVM framework (Sec. 3.1).  ... 
arXiv:1501.07492v2 fatcat:p3efba5itzhcrleg5g27ogjk6e

Deep Learning for Scene Classification: A Survey [article]

Delu Zeng, Minyu Liao, Mohammad Tavakolian, Yulan Guo, Bolei Zhou, Dewen Hu, Matti Pietikäinen, Li Liu
2021 arXiv   pre-print
Object detection determines whether or not any instance of the salient regions is presented in an image [107] .  ...  SUN RGBD dataset [72] consists of 10,335 RGB-D images with dense annotations in both 2D and 3D, for both objects and rooms.  ...  Currently, he is a Ph.D. student at the Center for Machine and Signal Analysis (CMVS) of the University of Oulu, Finland.  ... 
arXiv:2101.10531v2 fatcat:hwqw5so46ngxdlnfw7zynmpu6m

Deep Learning for X-ray Image to Text Generation

Mahima Chaddha, Sneha Kashid, Snehal Bhosale | Prof. Radha Deoghare
2019 International Journal of Trend in Scientific Research and Development  
Motivated by the recent success of supervised and weakly supervised common object discovery, in this work we move forward one step further to tackle common object discovery in a fully unsupervised way.  ...  Traditional object localization/ detection usually trains the specific object detectors which require bounding box annotations of object instances, or at least image-level labels to indicate the presence  ...  Weakly supervised Object localization(WSOL), has drawn much attention recently.  ... 
doi:10.31142/ijtsrd23168 fatcat:cmcw7kd6cbc7jmqm65wm3aebj4

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision [article]

Shiyi Lan, Zhiding Yu, Christopher Choy, Subhashree Radhakrishnan, Guilin Liu, Yuke Zhu, Larry S. Davis, Anima Anandkumar
2021 arXiv   pre-print
Our best model achieves 37.9% AP on COCO instance segmentation, surpassing prior weakly supervised methods and is competitive to supervised methods.  ...  We also obtain state of the art weakly supervised results on PASCAL VOC12 and PF-PASCAL with real-time inference.  ...  Learning pixel-level semantic [87] Hakan Bilen and Andrea Vedaldi. Weakly supervised deep affinity with image-level supervision for weakly supervised detection networks.  ... 
arXiv:2105.06464v2 fatcat:wr5iyiqvivb3novhhkgxwk6mv4

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TMM 2021 1330-1342 Joint Cross-Modal and Unimodal Features for RGB-D Salient Object Detection.  ...  ., +, TMM 2021 3179-3192 Joint Cross-Modal and Unimodal Features for RGB-D Salient Object Detection.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

A Review of Co-saliency Detection Technique: Fundamentals, Applications, and Challenges [article]

Dingwen Zhang, Huazhu Fu, Junwei Han, Ali Borji, Xuelong Li
2017 arXiv   pre-print
As a novel branch of visual saliency, co-saliency detection refers to the discovery of common and salient foregrounds from two or more relevant images, and can be widely used in many computer vision tasks  ...  Co-saliency detection is a newly emerging and rapidly growing research area in computer vision community.  ...  of weakly supervised object localization), while the information from image groups weakly labeled as containing other types of objects (i.e., the negative images in the task of weakly supervised object  ... 
arXiv:1604.07090v5 fatcat:j7zqwqaowndrbcuoazzizkuqr4

Video Object Segmentation and Tracking: A Survey [article]

Rui Yao, Guosheng Lin, Shixiong Xia, Jiaqi Zhao, Yong Zhou
2019 arXiv   pre-print
First, we provide a hierarchical categorization existing approaches, including unsupervised VOS, semi-supervised VOS, interactive VOS, weakly supervised VOS, and segmentation-based tracking methods.  ...  Object segmentation and object tracking are fundamental research area in the computer vision community.  ...  In Sec. 2.4, we discuss various weakly supervised information for video object segmentation.  ... 
arXiv:1904.09172v3 fatcat:nm3zptbidvgxfkxezqjekwdpdi

2019 Index IEEE Transactions on Circuits and Systems for Video Technology Vol. 29

2019 IEEE transactions on circuits and systems for video technology (Print)  
RGB-D Egocentric Action Recognition; TCSVT Oct. 2019 3001-3015 Tang, Y., Zou, W., Jin, Z., Chen, Y., Hua, Y., and Li, X., Weakly Supervised Salient Object Detection With Spatiotemporal Cascade Neural  ...  ., +, TCSVT Sept. 2019 2613-2626 Weakly Supervised Salient Object Detection With Spatiotemporal Cascade Neural Networks.  ... 
doi:10.1109/tcsvt.2019.2959179 fatcat:2bdmsygnonfjnmnvmb72c63tja

Human Action Recognition and Prediction: A Survey [article]

Yu Kong, Yun Fu
2022 arXiv   pre-print
Many attempts have been devoted in the last a few decades in order to build a robust and effective framework for action recognition and prediction.  ...  [315] introduced the temporal structure mining (TSM) approach to the weakly-supervised action detection problem.  ...  [277] proposed a weakly-supervised action detection model that is directly learned on the untrimmed video data, achieving performance on-par-with those of the full-supervised action detection methods  ... 
arXiv:1806.11230v3 fatcat:2a2d7fuezbdqzfgrjwkcuqvmbu
« Previous Showing results 1 — 15 out of 154 results