Search

Your search keyword '"Shangchen Zhou"' showing total 71 results
Start Over Author "Shangchen Zhou"
71 results on '"Shangchen Zhou"'

2. MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results.

Author

Xin Jin 0005, Chunle Guo, Xiaoming Li 0002, Zongsheng Yue, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Yuekun Dai, Peiqing Yang, Chen Change Loy, Ruoqi Li, Chang Liu 0030, Ziyi Wang 0006, Yao Du, Jingjing Yang, Long Bao, Heng Sun, Xiangyu Kong, Xiaoxia Xing, Jinlong Wu, Yuanyang Xue, Hyunhee Park, Sejun Song, Changho Kim, Jingfan Tan, Wenhan Luo, Zikun Liu, Mingde Qiao, Junjun Jiang, Kui Jiang, Yao Xiao, Chuyang Sun, Jinhui Hu, Weijian Ruan, Yubo Dong, Kai Chen 0026, Hyejeong Jo, Jiahao Qin, Bingjie Han, Pinle Qin, Rui Chai, and Pengyuan Wang

Published
2024
Full Text
View/download PDF

11. MIPI 2023 Challenge on RGBW Remosaic: Methods and Results.

Author

Qianhui Sun, Qingyu Yang, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Yuekun Dai, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu, Yuqing Liu, Hongyuan Yu, Weichen Yu, Zhen Dong, Binnan Han, Qi Jia, Xuanwu Yin, Kunlong Zuo, Yaqi Wu, Zhihao Fan, Fanqing Meng, Xun Wu, Jiawei Zhang 0002, Feng Zhang, Mingyan Han, Jinting Luo, Qi Wu 0017, Ting Jiang, Chengzhi Jiang, Wenjie Lin, Xinpeng Li, Lei Yu, Haoqiang Fan, and Shuaicheng Liu

Published
2023
Full Text
View/download PDF

13. MIPI 2023 Challenge on Nighttime Flare Removal: Methods and Results.

Author

Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Qingpeng Zhu, Qianhui Sun, Wenxiu Sun, Chen Change Loy, Jinwei Gu, Shuai Liu 0009, Hao Wang 0073, Chaoyu Feng, Luyang Wang, Guangqi Shao, Chenguang Zhang, Xiaotao Wang, Lei Lei, Dafeng Zhang, Xiangyu Kong, Guanqun Liu 0005, Mengmeng Bai, Jia Ouyang, Xiaobing Wang, Jiahui Yuan, Xinpeng Li, Chengzhi Jiang, Ting Jiang, Wenjie Lin, Qi Wu 0017, Mingyan Han, Jinting Luo, Lei Yu, Haoqiang Fan, Shuaicheng Liu, Bo Yan, Zhuang Li, Yadong Li, Hongbin Wang, Soonyong Song, Minghan Fu, Rayyan Azam Khan, Fang-Xiang Wu, Zhao Zhang 0001, Suiyi Zhao, Huan Zheng, Yangcheng Gao, Yanyan Wei, Jiahuan Ren, Bo Wang 0011, Yan Luo, Shuaibo Gao, Wenhui Wu, Sicong Kang, Nikhil Akalwadi, Ankit Raichur, Vinod Patil, Allabakash Ghodesawar, Swaroop Adrashyappanamath, Amogh Joshi, Chaitra Desai, Ramesh Ashok Tabib, Ujwala Patil, Uma Mudenagudi, Sicheng Li, Ruoxi Zhu, Jiazheng Lian, Shusong Xu, Zihao Liu, Sabari Nathan, and Priya Kansal

Published
2023
Full Text
View/download PDF

14. MIPI 2023 Challenge on RGB+ToF Depth Completion: Methods and Results.

Author

Qingpeng Zhu, Wenxiu Sun, Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Qianhui Sun, Chen Change Loy, Jinwei Gu, Yi Yu, Yangke Huang, Kang Zhang, Meiya Chen, Yu Wang, Yongchao Li, Hao Jiang, Amrit Kumar Muduli, Vikash Kumar, Kunal Swami, Pankaj Kumar Bajpai, Yunchao Ma, Jiajun Xiao, and Zhi Ling

Published
2023
Full Text
View/download PDF

16. MIPI 2023 Challenge on RGBW Fusion: Methods and Results.

Author

Qianhui Sun, Qingyu Yang, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Yuekun Dai, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu, Hongyuan Yu, Yuqing Liu, Weichen Yu, Lin Ge, Xiaolin Zhang, Qi Jia, Heng Zhang, Xuanwu Yin, Kunlong Zuo, Qi Wu 0017, Wenjie Lin, Ting Jiang, Chengzhi Jiang, Mingyan Han, Xinpeng Li, Jinting Luo, Lei Yu, Haoqiang Fan, Shuaicheng Liu, Kunyu Wang, Chengzhi Cao, Yuanshen Guan, Jiyuan Xia, Ruikang Xu, Mingde Yao, and Zhiwei Xiong

Published
2023
Full Text
View/download PDF

18. NTIRE 2022 Challenge on Night Photography Rendering.

Author

Egor I. Ershov, Alexey Savchik, Denis A. Shepelev, Nikola Banic, Michael S. Brown, Radu Timofte, Karlo Koscevic, Michael Freeman, Vasily Tesalin, Dmitry Bocharov, Illya Semenkov, Marko Subasic, Sven Loncaric, Arseniy P. Terekhin, Shuai Liu 0009, Chaoyu Feng, Hao Wang 0073, Ran Zhu, Yongqiang Li, Lei Lei, Zhihao Li, Si Yi, Linghao Han, Ruiqi Wu, Xin Jin 0005, Chunle Guo, Furkan Kinli, Sami Mentes, Baris özcan, Furkan Kiraç, Simone Zini, Claudio Rota, Marco Buzzelli, Simone Bianco 0001, Raimondo Schettini, Wei Li 0002, Yipeng Ma, Tao Wang, Ruikang Xu, Fenglong Song, Wei-Ting Chen, Hao-Hsiang Yang, Zhi-Kai Huang, Hua-En Chang, Sy-Yen Kuo, Zhexin Liang, Shangchen Zhou, Ruicheng Feng, Chongyi Li, Xiangyu Chen 0006, Binbin Song, Shile Zhang, Lin Liu 0016, Zhendong Wang, Dohoon Ryu, Hyokyoung Bae, Taesung Kwon, Chaitra Desai, Nikhil Akalwadi, Amogh Joshi, Chinmayee Mandi, Sampada Malagi, Akash Uppin, Sai Sudheer Reddy, Ramesh Ashok Tabib, Ujwala Patil, and Uma Mudenagudi

Published
2022
Full Text
View/download PDF

20. MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Report.

Author

Wenxiu Sun, Qingpeng Zhu, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Jun Jiang, Qingyu Yang, Chen Change Loy, Jinwei Gu, Dewang Hou, Kai Zhao, Liying Lu, Yu Li 0003, Huaijia Lin, Ruizheng Wu, Jiangbo Lu, Jiaya Jia, Qiang Liu, Haosong Yue, Danyang Cao, Lehang Yu, Jiaxuan Quan, Jixiang Liang, Yufei Wang, Yuchao Dai, Peng Yang, Hu Yan, Houbiao Liu, Siyuan Su, Xuanhe Li, Rui Ren, Yunlong Liu, Yufan Zhu, Dong Lao, Alex Wong 0001, and Katie Chang

Published
2022
Full Text
View/download PDF

21. MIPI 2022 Challenge on Quad-Bayer Re-mosaic: Dataset and Report.

Author

Qingyu Yang, Guang Yang, Jun Jiang, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu, Zhen Wang 0029, Daoyu Li, Yuzhe Zhang, Lintao Peng, Xuyang Chang, Yinuo Zhang, Yaqi Wu, Xun Wu, Zhihao Fan, Chengjie Xia, Feng Zhang, Haijin Zeng, Kai Feng, Yongqiang Zhao 0001, Hiêp Quang Luong, Jan Aelterman, Anh Minh Truong, Wilfried Philips, Xiaohong Liu 0001, Jun Jia, Hanchi Sun, Guangtao Zhai, Longan Xiao, Qihang Xu, Ting Jiang, Qi Wu 0017, Chengzhi Jiang, Mingyan Han, Xinpeng Li, Wenjie Lin, Youwei Li, Haoqiang Fan, Shuaicheng Liu, Rongyuan Wu, Lingchen Sun, and Qiaosi Yi

Published
2022
Full Text
View/download PDF

23. MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results.

Author

Ruicheng Feng, Chongyi Li, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Jun Jiang, Qingyu Yang, Chen Change Loy, Jinwei Gu, Yurui Zhu, Xi Wang, Xueyang Fu, Xiaowei Hu, Jinfan Hu, Xina Liu, Xiangyu Chen 0006, Chao Dong 0005, Dafeng Zhang, Feiyu Huang, Shizhuo Liu, Xiaobing Wang, Zhezhu Jin, Xuhao Jiang, Guangqi Shao, Xiaotao Wang, Lei Lei, Zhao Zhang 0001, Suiyi Zhao, Huan Zheng, Yangcheng Gao, Yanyan Wei, Jiahuan Ren, Tao Huang, Zhenxuan Fang, Mengluan Huang, Junwei Xu, Yong Zhang, Yuechi Yang, Qidi Shu, Zhiwen Yang, Shaocong Li, Mingde Yao, Ruikang Xu, Yuanshen Guan, Jie Huang 0017, Zhiwei Xiong, Hangyan Zhu, Ming Liu, Shaohui Liu, Wangmeng Zuo, Zhuang Jia, Binbin Song, Ziqi Song, Guiting Mao, Ben Hou, Zhimou Liu, Yi Ke, Dengpei Ouyang, Dekui Han, Jinghao Zhang, Qi Zhu 0010, Naishan Zheng, Feng Zhao 0004, Wu Jin, Marcos V. Conde, Sabari Nathan, Radu Timofte, Tianyi Xu, Jun Xu 0019, P. S. Hrishikesh, Densen Puthussery, C. V. Jiji, Biao Jiang, Yuhan Ding, WanZhang Li, Xiaoyue Feng, Sijing Chen, Tianheng Zhong, Jiyang Lu, Hongming Chen 0004, Zhentao Fan, and Xiang Chen 0015

Published
2022
Full Text
View/download PDF

25. MIPI 2022 Challenge on RGBW Sensor Fusion: Dataset and Report.

Author

Qingyu Yang, Guang Yang, Jun Jiang, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu, Zhen Wang 0029, Daoyu Li, Yuzhe Zhang, Lintao Peng, Xuyang Chang, Yinuo Zhang, Liheng Bian, Bing Li 0024, Jie Huang 0017, Mingde Yao, Ruikang Xu, Feng Zhao 0004, Xiaohui Liu 0003, Rongjian Xu, Zhilu Zhang, Xiaohe Wu, Ruohao Wang, Junyi Li, Wangmeng Zuo, Zhuang Jia, DongJae Lee, Ting Jiang, Qi Wu 0017, Chengzhi Jiang, Mingyan Han, Xinpeng Li, Wenjie Lin, Youwei Li, Haoqiang Fan, and Shuaicheng Liu

Published
2022
Full Text
View/download PDF

42. Deep Dynamic Scene Deblurring from Optical Flow

Author

Jinshan Pan, Shangchen Zhou, Zhao Furong, Daoye Wang, Jianbo Liu, Jimmy Ren, Jiawei Zhang, and Xing Wei

Subjects
FOS: Computer and information sciences, Deblurring, business.industry, Computer science, Computer Vision and Pattern Recognition (cs.CV), Photography, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Optical flow, Computer Science - Computer Vision and Pattern Recognition, Tracking (particle physics), Convolutional neural network, Recurrent neural network, Feature (computer vision), Media Technology, Benchmark (computing), Computer vision, Artificial intelligence, Electrical and Electronic Engineering, business
Abstract

Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as tracking. However, removing dynamic scene blur from images is a non-trivial task as it is difficult to model the non-uniform blur mathematically. Several methods first use single or multiple images to estimate optical flow (which is treated as an approximation of blur kernels) and then adopt non-blind deblurring algorithms to reconstruct the sharp images. However, these methods cannot be trained in an end-to-end manner and are usually computationally expensive. In this paper, we explore optical flow to remove dynamic scene blur by using the multi-scale spatially variant recurrent neural network (RNN). We utilize FlowNets to estimate optical flow from two consecutive images in different scales. The estimated optical flow provides the RNN weights in different scales so that the weights can better help RNNs to remove blur in the feature spaces. Finally, we develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features. Both quantitative and qualitative evaluations on the benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of accuracy, speed, and model size., accepted by tcsvt

Published
2023

43. MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results

Author

Ruicheng Feng, Chongyi Li, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Jun Jiang, Qingyu Yang, Chen Change Loy, Jinwei Gu, Yurui Zhu, Xi Wang, Xueyang Fu, Xiaowei Hu, Jinfan Hu, Xina Liu, Xiangyu Chen, Chao Dong, Dafeng Zhang, Feiyu Huang, Shizhuo Liu, Xiaobing Wang, Zhezhu Jin, Xuhao Jiang, Guangqi Shao, Xiaotao Wang, Lei Lei, Zhao Zhang, Suiyi Zhao, Huan Zheng, Yangcheng Gao, Yanyan Wei, Jiahuan Ren, Tao Huang, Zhenxuan Fang, Mengluan Huang, Junwei Xu, Yong Zhang, Yuechi Yang, Qidi Shu, Zhiwen Yang, Shaocong Li, Mingde Yao, Ruikang Xu, Yuanshen Guan, Jie Huang, Zhiwei Xiong, Hangyan Zhu, Ming Liu, Shaohui Liu, Wangmeng Zuo, Zhuang Jia, Binbin Song, Ziqi Song, Guiting Mao, Ben Hou, Zhimou Liu, Yi Ke, Dengpei Ouyang, Dekui Han, Jinghao Zhang, Qi Zhu, Naishan Zheng, Feng Zhao, Wu Jin, Marcos Conde, Sabari Nathan, Radu Timofte, Tianyi Xu, Jun Xu, P. S. Hrishikesh, Densen Puthussery, C. V. Jiji, Biao Jiang, Yuhan Ding, WanZhang Li, Xiaoyue Feng, Sijing Chen, Tianheng Zhong, Jiyang Lu, Hongming Chen, Zhentao Fan, and Xiang Chen

Published
2023

44. MIPI 2022 Challenge on Quad-Bayer Re-mosaic: Dataset and Report

Author

Qingyu Yang, Guang Yang, Jun Jiang, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu, Zhen Wang, Daoyu Li, Yuzhe Zhang, Lintao Peng, Xuyang Chang, Yinuo Zhang, Yaqi Wu, Xun Wu, Zhihao Fan, Chengjie Xia, Feng Zhang, Haijin Zeng, Kai Feng, Yongqiang Zhao, Hiep Quang Luong, Jan Aelterman, Anh Minh Truong, Wilfried Philips, Xiaohong Liu, Jun Jia, Hanchi Sun, Guangtao Zhai, Longan Xiao, Qihang Xu, Ting Jiang, Qi Wu, Chengzhi Jiang, Mingyan Han, Xinpeng Li, Wenjie Lin, Youwei Li, Haoqiang Fan, Shuaicheng Liu, Rongyuan Wu, Lingchen Sun, and Qiaosi Yi

Published
2023

45. MIPI 2022 Challenge on RGBW Sensor Re-mosaic: Dataset and Report

Author

Qingyu Yang, Guang Yang, Jun Jiang, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu, Lingchen Sun, Rongyuan Wu, Qiaosi Yi, Rongjian Xu, Xiaohui Liu, Zhilu Zhang, Xiaohe Wu, Ruohao Wang, Junyi Li, Wangmeng Zuo, and Faming Fang

Published
2023

46. MIPI 2022 Challenge on RGBW Sensor Fusion: Dataset and Report

Author

Qingyu Yang, Guang Yang, Jun Jiang, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu, Zhen Wang, Daoyu Li, Yuzhe Zhang, Lintao Peng, Xuyang Chang, Yinuo Zhang, Liheng Bian, Bing Li, Jie Huang, Mingde Yao, Ruikang Xu, Feng Zhao, Xiaohui Liu, Rongjian Xu, Zhilu Zhang, Xiaohe Wu, Ruohao Wang, Junyi Li, Wangmeng Zuo, Zhuang Jia, DongJae Lee, Ting Jiang, Qi Wu, Chengzhi Jiang, Mingyan Han, Xinpeng Li, Wenjie Lin, Youwei Li, Haoqiang Fan, and Shuaicheng Liu

Published
2023

47. MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Report

Author

Wenxiu Sun, Qingpeng Zhu, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Jun Jiang, Qingyu Yang, Chen Change Loy, Jinwei Gu, Dewang Hou, Kai Zhao, Liying Lu, Yu Li, Huaijia Lin, Ruizheng Wu, Jiangbo Lu, Jiaya Jia, Qiang Liu, Haosong Yue, Danyang Cao, Lehang Yu, Jiaxuan Quan, Jixiang Liang, Yufei Wang, Yuchao Dai, Peng Yang, Hu Yan, Houbiao Liu, Siyuan Su, Xuanhe Li, Rui Ren, Yunlong Liu, Yufan Zhu, Dong Lao, Alex Wong, and Katie Chang

Published
2023

48. Toward 3D object reconstruction from stereo images

Author

Haozhe Xie, Hongxun Yao, Wenxiu Sun, Shengping Zhang, Xiaojun Tong, and Shangchen Zhou

Subjects
Structure (mathematical logic), Stereo cameras, business.industry, Generalization, Computer science, Cognitive Neuroscience, Deep learning, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Object (computer science), Computer Science Applications, Artificial Intelligence, Feature (computer vision), Benchmark (computing), Robot, Computer vision, Artificial intelligence, business
Abstract

Inferring the complete 3D shape of an object from an RGB image has shown impressive results, however, existing methods rely primarily on recognizing the most similar 3D model from the training set to solve the problem. These methods suffer from poor generalization and may lead to low-quality reconstructions for unseen objects. Nowadays, stereo cameras are pervasive in emerging devices such as dual-lens smartphones and robots, which enables the use of the two-view nature of stereo images to explore the 3D structure and thus improve the reconstruction performance. In this paper, we propose a new deep learning framework for reconstructing the 3D shape of an object from a pair of stereo images, which reasons about the 3D structure of the object by taking bidirectional disparities and feature correspondences between the two views into account. Besides, we present a large-scale synthetic benchmarking dataset, namely StereoShapeNet, containing 1,052,976 pairs of stereo images rendered from ShapeNet along with the corresponding bidirectional depth and disparity maps. Experimental results on the StereoShapeNet benchmark demonstrate that the proposed framework outperforms the state-of-the-art methods. The project page is available at https://haozhexie.com/project/stereo-3d-reconstruction .

Published
2021

49. NTIRE 2022 Challenge on Night Photography Rendering

Author

Egor Ershov, Alex Savchik, Denis Shepelev, Nikola Banic, Michael S. Brown, Radu Timofte, Karlo Koscevic, Michael Freeman, Vasily Tesalin, Dmitry Bocharov, Illya Semenkov, Marko Subasic, Sven Loncaric, Arseniy Terekhin, Shuai Liu, Chaoyu Feng, Hao Wang, Ran Zhu, Yongqiang Li, Lei Lei, Zhihao Li, Si Yi, Ling-Hao Han, Ruiqi Wu, Xin Jin, Chunle Guo, Furkan Kinli, Sami Mentes, Baris Ozcan, Furkan Kirac, Simone Zini, Claudio Rota, Marco Buzzelli, Simone Bianco, Raimondo Schettini, Wei Li, Yipeng Ma, Tao Wang, Ruikang Xu, Fenglong Song, Wei-Ting Chen, Hao-Hsiang Yang, Zhi-Kai Huang, Hua-En Chang, Sy-Yen Kuo, Zhexin Liang, Shangchen Zhou, Ruicheng Feng, Chongyi Li, Xiangyu Chen, Binbin Song, Shile Zhang, Lin Liu, Zhendong Wang, Dohoon Ryu, Hyokyoung Bae, Taesung Kwon, Chaitra Desai, Nikhil Akalwadi, Amogh Joshi, Chinmayee Mandi, Sampada Malagi, Akash Uppin, Sai Sudheer Reddy, Ramesh Ashok Tabib, Ujwala Patil, Uma Mudenagudi, Ershov, E, Savchik, A, Shepelev, D, Banic, N, Brown, M, Timofte, R, Koscevic, K, Freeman, M, Tesalin, V, Bocharov, D, Semenkov, I, Subasic, M, Loncaric, S, Terekhin, A, Liu, S, Feng, C, Wang, H, Zhu, R, Li, Y, Lei, L, Li, Z, Yi, S, Han, L, Wu, R, Jin, X, Guo, C, Kinli, F, Mentes, S, Ozcan, B, Kirac, F, Zini, S, Rota, C, Buzzelli, M, Bianco, S, Schettini, R, Li, W, Ma, Y, Wang, T, Xu, R, Song, F, Chen, W, Yang, H, Huang, Z, Chang, H, Kuo, S, Liang, Z, Zhou, S, Feng, R, Li, C, Chen, X, Song, B, Zhang, S, Liu, L, Wang, Z, Ryu, D, Bae, H, Kwon, T, Desai, C, Akalwadi, N, Joshi, A, Mandi, C, Malagi, S, Uppin, A, Sudheer Reddy, S, Ashok Tabib, R, Patil, U, and Mudenagudi, U

Subjects
night photography, Photography, Visualization, Computer vision, Conferences, Rendering (computer graphics), Cameras, Pattern recognition
Abstract

This paper reviews the NTIRE 2022 challenge on night photography rendering. The challenge solicited solutions that processed RAW camera images captured in night scenes to produce a photo-finished output image encoded in the standard RGB (sRGB) space. Given the subjective nature of this task, the proposed solutions were evaluated based on the mean opinions of viewers asked to judge the visual appearance of the results. Michael Freeman, a world-renowned photographer, further ranked the solutions with the highest mean opinion scores. A total of 13 teams competed in the final phase of the challenge. The proposed methods provided by the participating teams represent state-of-the-art performance in nighttime photography. Results from the various teams can be found here: https://nightimaging.org/

Published
2022

50. Deep Saliency Hashing for Fine-Grained Retrieval

Author

Lei Zhang, Sheng Jin, Hongxun Yao, Xian-Sheng Hua, Xiaoshuai Sun, and Shangchen Zhou

Subjects
Computer science, business.industry, Quantization (signal processing), Hash function, Pattern recognition, 02 engineering and technology, Computer Graphics and Computer-Aided Design, Search engine, Discriminative model, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, business, Software
Abstract

In recent years, hashing methods have been proved to be effective and efficient for large-scale Web media search. However, the existing general hashing methods have limited discriminative power for describing fine-grained objects that share similar overall appearance but have a subtle difference. To solve this problem, we for the first time introduce the attention mechanism to the learning of fine-grained hashing codes. Specifically, we propose a novel deep hashing model, named deep saliency hashing (DSaH), which automatically mines salient regions and learns semantic-preserving hashing codes simultaneously. DSaH is a two-step end-to-end model consisting of an attention network and a hashing network. Our loss function contains three basic components, including the semantic loss, the saliency loss, and the quantization loss. As the core of DSaH, the saliency loss guides the attention network to mine discriminative regions from pairs of images. We conduct extensive experiments on both fine-grained and general retrieval datasets for performance evaluation. Experimental results on fine-grained datasets, including Oxford Flowers, Stanford Dogs, and CUB Birds demonstrate that our DSaH performs the best for the fine-grained retrieval task and beats the strongest competitor (DTQ) by approximately 10% on both Stanford Dogs and CUB Birds. DSaH is also comparable to several state-of-the-art hashing methods on CIFAR-10 and NUS-WIDE.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results