67,304 Hits in 4.6 sec

Proposal Learning for Semi-Supervised Object Detection [article]

Peng Tang, Chetan Ramaiah, Yan Wang, Ran Xu, Caiming Xiong
2020 arXiv   pre-print
object detection; 3) building a general and high-performance semi-supervised object detection framework, which can be easily adapted to proposal-based object detectors with different backbone architectures  ...  In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data.  ...  Here we further apply self-supervised learning to SSOD by a self-supervised proposal learning module. Semi-supervised object detection applies semi-supervised learning to object detection.  ... 
arXiv:2001.05086v2 fatcat:mibve7n645fbxblssatwyqchtm

Interpolation-based semi-supervised learning for object detection [article]

Jisoo Jeong, Vikas Verma, Minsung Hyun, Juho Kannala, Nojun Kwak
2020 arXiv   pre-print
Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied  ...  In this paper, we propose an Interpolation-based Semi-supervised learning method for object Detection (ISD), which considers and solves the problems caused by applying conventional Interpolation Regularization  ...  Semi-supervised learning for object detection has recently been studied in [13] where CSD, the first consistency-regularization-based semi-supervised object detection method, was proposed.  ... 
arXiv:2006.02158v2 fatcat:voqlt3irerazvn2tbzoxn2zy7m

SESS: Self-Ensembling Semi-Supervised 3D Object Detection [article]

Na Zhao, Tat-Seng Chua, Gim Hee Lee
2021 arXiv   pre-print
Semi-supervised learning is a good alternative to mitigate the data annotation issue, but has remained largely unexplored in 3D object detection.  ...  Inspired by the recent success of self-ensembling technique in semi-supervised image classification task, we propose SESS, a self-ensembling semi-supervised 3D object detection framework.  ...  Semi-supervised learning is a promising alternative to strongly supervised learning for point cloud-based 3D object detection.  ... 
arXiv:1912.11803v3 fatcat:7tmdcso3bbfcpobzjho2hlhega

One Million Scenes for Autonomous Driving: ONCE Dataset [article]

Jiageng Mao, Minzhe Niu, Chenhan Jiang, Hanxue Liang, Jingheng Chen, Xiaodan Liang, Yamin Li, Chaoqiang Ye, Wei Zhang, Zhenguo Li, Jie Yu, Hang Xu (+1 others)
2021 arXiv   pre-print
To facilitate future research on exploiting unlabeled data for 3D detection, we additionally provide a benchmark in which we reproduce and evaluate a variety of self-supervised and semi-supervised methods  ...  In this paper, we introduce the ONCE (One millioN sCenEs) dataset for 3D object detection in the autonomous driving scenario.  ...  Semi-Supervised Learning for 3D Object Detection We implement 3 image-based semi-supervised methods: Pseudo Label [25] , Mean Teacher [41] and Noisy Student [47] , as well as 2 semi-supervised methods  ... 
arXiv:2106.11037v3 fatcat:fwgrb57yarhujmetzpewtdzzei

Semi-supervised Learning for Dense Object Detection in Retail Scenes [article]

Jaydeep Chauhan, Srikrishna Varadarajan, Muktabh Mayank Srivastava
2021 arXiv   pre-print
We adapt a popular self supervised method called noisy student initially proposed for object classification to the task of dense object detection.  ...  Hence, we propose semi-supervised learning to effectively use the large amount of unlabeled data available in the retail domain.  ...  Hence we resort to a semi-supervised learning using the noisy student training method [30] . It is a semi-supervised based approach to train our model on a combination of labeled and unlabeled data.  ... 
arXiv:2107.02114v1 fatcat:yqodx3cpk5brzabttpmm64cugy

Improving Object Detection with Selective Self-supervised Self-training [article]

Yandong Li, Di Huang, Danfeng Qin, Liqiang Wang, Boqing Gong
2020 arXiv   pre-print
On the other hand, we propose a novel learning method motivated by two parallel lines of work that explore unlabeled data for image classification: self-training and self-supervised learning.  ...  We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged.  ...  CSD [26] : We include the recently published consistency-based semi-supervised object detection (CSD) in the experiments.  ... 
arXiv:2007.09162v2 fatcat:jubt7f4alje47ghb3c7jntpyfa

Deep Semi-supervised Metric Learning with Dual Alignment for Cervical Cancer Cell Detection [article]

Zhizhong Chai, Luyang Luo, Huangjing Lin, Hao Chen, Anjia Han, Pheng-Ann Heng
2022 arXiv   pre-print
In this paper, we propose a novel deep semi-supervised metric learning method to effectively leverage both labeled and unlabeled data for cervical cancer cell detection.  ...  Extensive experiments show our proposed method outperforms other state-of-the-art semi-supervised approaches consistently, demonstrating the efficacy of our proposed deep semi-supervised metric learning  ...  Recently, many semi-supervised object detection methods have been proposed under different application scenarios. A broad branch of works was based on knowledge distillation. For example, Wang et al.  ... 
arXiv:2104.03265v2 fatcat:kzchmda7u5bmpg42oqbf3ywl3e

End-to-End Semi-Supervised Learning for Video Action Detection [article]

Akash Kumar, Yogesh Singh Rawat
2022 arXiv   pre-print
In this work, we focus on semi-supervised learning for video action detection which utilizes both labeled as well as unlabeled data.  ...  We propose a simple end-to-end consistency based approach which effectively utilizes the unlabeled data.  ...  Thus, it effectively works similar to any consistency-based object-detection for images.  ... 
arXiv:2203.04251v2 fatcat:uxdwbrsxmfbf7e4233i7dkp3tq

Semi-supervised 3D Object Detection via Temporal Graph Neural Networks [article]

Jianren Wang, Haiming Gang, Siddarth Ancha, Yi-Ting Chen, David Held
2022 arXiv   pre-print
Instead, we propose leveraging large amounts of unlabeled point cloud videos by semi-supervised learning of 3D object detectors via temporal graph neural networks.  ...  After semi-supervised learning, our method achieves state-of-the-art detection performance on the challenging nuScenes and H3D benchmarks, compared to baselines trained on the same amount of labeled data  ...  The authors would like to thank members of R-pad for fruitful discussion and detailed feedback on the manuscript.  ... 
arXiv:2202.00182v1 fatcat:n7fptukzh5aabhvsrhtaj4ufle

Freeway Traffic Incident Detection from Cameras: A Semi-Supervised Learning Approach

Pranamesh Chakraborty, Anuj Sharma, Chinmay Hegde
2018 2018 21st International Conference on Intelligent Transportation Systems (ITSC)  
In this study, we used semi-supervised techniques to detect traffic incident trajectories from the cameras.  ...  We compared the performance of CPLE algorithm to traditional semi-supervised techniques Self Learning and Label Spreading, and also to the classification based on the corresponding supervised algorithm  ...  Vehicle detection is performed using state-of-art deep learning based YOLOv3 and SORT tracker is used for tracking.  ... 
doi:10.1109/itsc.2018.8569426 dblp:conf/itsc/ChakrabortySH18 fatcat:tfvya2u2jvgq3bniwd5wceft2i

Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification [article]

Zhenyu Wang, Yali Li, Ye Guo, Shengjin Wang
2021 arXiv   pre-print
In this paper, we delve into semi-supervised learning for object detection, where labeled data are more labor-intensive to collect.  ...  Semi-supervised learning aims to leverage a large amount of unlabeled data for performance boosting. Existing works primarily focus on image classification.  ...  In this paper, we propose a region uncertainty quantification based semi-supervised learning method for object detection.  ... 
arXiv:2111.00928v1 fatcat:tfwlqladajf3jivipmgt7cesym

A Simple Semi-Supervised Learning Framework for Object Detection [article]

Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li, Han Zhang, Chen-Yu Lee, Tomas Pfister
2020 arXiv   pre-print
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.  ...  We propose experimental protocols to evaluate the performance of semi-supervised object detection using MS-COCO and show the efficacy of STAC on both MS-COCO and VOC07.  ...  Recently, [23] proposes a consistency-based semi-supervised object detection method, which enforces the consistent prediction of an unlabeled image and its flipped counterpart.  ... 
arXiv:2005.04757v2 fatcat:qney5wxuebcc5dljxvdrf3lfzi

Grasping Detection Network with Uncertainty Estimation for Confidence-Driven Semi-Supervised Domain Adaptation [article]

Haiyue Zhu, Yiting Li, Fengjun Bai, Wenjie Chen, Xiaocong Li, Jun Ma, Chek Sing Teo, Pey Yuen Tao, Wei Lin
2020 arXiv   pre-print
This paper presents an approach enabling the easy domain adaptation through a novel grasping detection network with confidence-driven semi-supervised learning, where these two components deeply interact  ...  The proposed grasping detection network specially provides a prediction uncertainty estimation mechanism by leveraging on Feature Pyramid Network (FPN), and the mean-teacher semi-supervised learning utilizes  ...  Semi-Supervised Learning Semi-supervised learning exploits the unlabelled data to provide the regularization for reducing the model overfitting.  ... 
arXiv:2008.08817v1 fatcat:6u2lmzyl6zhtzkgp2fkujdtxvm


E. Bousias Alexakis, C. Armenakis
2021 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The approach is based on the Mean Teacher method, a semi-supervised approach, successfully applied for image classification and for sematic segmentation of medical images.  ...  Research is continuing towards fine-tuning of the method and reaching solid conclusions with respect to the potential benefits of the semi-supervised learning approaches in image change detection applications  ...  The Change Detection Dataset was provided by Lebedev et al., 2018: to-nHrNs9  ... 
doi:10.5194/isprs-archives-xliii-b3-2021-829-2021 fatcat:de3tnxo6sndlzayzc2zi5kctme

SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving [article]

Jianhua Han, Xiwen Liang, Hang Xu, Kai Chen, Lanqing Hong, Jiageng Mao, Chaoqiang Ye, Wei Zhang, Zhenguo Li, Xiaodan Liang, Chunjing Xu
2021 arXiv   pre-print
Here, we release a Large-Scale 2D Self/semi-supervised Object Detection dataset for Autonomous driving, named as SODA10M, containing 10 million unlabeled images and 20K images labeled with 6 representative  ...  Motivated by recent advances of self-supervised and semi-supervised learning, a promising direction is to learn a robust detection model by collaboratively exploiting large-scale unlabeled data and few  ...  We thank our two data suppliers, named Testin 3 and Speechocean 4 (collected from King-IM-055), for helping us collect and annotate SODA10M dataset.  ... 
arXiv:2106.11118v3 fatcat:wtypjknlrbc4vp7yrygit4qxna
« Previous Showing results 1 — 15 out of 67,304 results