For the region perspective, we introduce Region Evaluate Module (REM) which uses a new and efficient sampling method for proposal feature representation containing more contextual information compared with point feature to refine category score and proposal boundary.
Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data.
Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video; ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information.
To this end, we propose to learn pixel-level distinctions to improve the video highlight detection.
This shows that DMA-Net provides a good tradeoff between segmentation quality and speed for semantic segmentation in street scenes.
Creative image animations are attractive in e-commerce applications, where motion transfer is one of the import ways to generate animations from static images.
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc.
In this paper, we propose a novel face recognition method, named VirFace, to effectively apply the unlabeled shallow data for face recognition.
Specifically, to alleviate the instability among the detection results in different iterations, we propose using nonmaximum suppression to fuse the detection results from different iterations.
This is because the classification paradigm needs to train a fully connected layer as the category classifier, and its parameters will be in the hundreds of millions if the training dataset contains millions of identities.
A new analytical framework consisting of two phenomena: single sample and multiple samples, is proposed to deal with the identification problem of Boolean control networks (BCNs) systematically and comprehensively.
We theoretically and experimentally demonstrate a novel mode-locked ytterbium-doped fiber laser with a saturable absorber based on nonlinear Kerr beam cleanup effect.
no code implementations • 30 Apr 2020 • Fei Tang, Wanling Gao, Jianfeng Zhan, Chuanxin Lan, Xu Wen, Lei Wang, Chunjie Luo, Jiahui Dai, Zheng Cao, Xingwang Xiong, Zihan Jiang, Tianshu Hao, Fanda Fan, Fan Zhang, Yunyou Huang, Jianan Chen, Mengjia Du, Rui Ren, Chen Zheng, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent.
no code implementations • 17 Feb 2020 • Wanling Gao, Fei Tang, Jianfeng Zhan, Chuanxin Lan, Chunjie Luo, Lei Wang, Jiahui Dai, Zheng Cao, Xiongwang Xiong, Zihan Jiang, Tianshu Hao, Fanda Fan, Xu Wen, Fan Zhang, Yunyou Huang, Jianan Chen, Mengjia Du, Rui Ren, Chen Zheng, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Gang Lu, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application.
The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data.
Renewable energy such as solar power is critical to fight the ever more serious climate change.
To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data stream over time without forgetting the previous knowledge.
no code implementations • 13 Aug 2019 • Wanling Gao, Fei Tang, Lei Wang, Jianfeng Zhan, Chunxin Lan, Chunjie Luo, Yunyou Huang, Chen Zheng, Jiahui Dai, Zheng Cao, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Tong Wu, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye
On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales.