1 code implementation • 4 Apr 2023 • Tianchen Zhou, Zhanyi Hu, Bingzhe Wu, Cen Chen
Data privacy concerns has made centralized training of data, which is scattered across silos, infeasible, leading to the need for collaborative learning frameworks.
no code implementations • 30 Mar 2022 • Bo Liu, Lihua Hu, Qiulei Dong, Zhanyi Hu
How to generate pseudo labels for unseen-class samples and how to use such usually noisy pseudo labels are two critical issues in transductive learning.
no code implementations • 17 Mar 2022 • Bo Liu, Qiulei Dong, Zhanyi Hu
Firstly, we propose a Semantic-diversity transfer Network (SetNet) addressing the first two limitations, where 1) a multiple-attention architecture and a diversity regularizer are proposed to learn multiple local visual features that are more consistent with semantic attributes and 2) a projector ensemble that geometrically takes diverse local features as inputs is proposed to model visual-semantic relations from diverse local perspectives.
no code implementations • 16 Jan 2022 • Pinhe Wang, Limin Shi, Bao Chen, Zhanyi Hu, Qiulei Dong, Jianzhong Qiao
How to use multiple optical satellite images to recover the 3D scene structure is a challenging and important problem in the remote sensing field.
no code implementations • 14 Jan 2022 • Bo Liu, Lihua Hu, Zhanyi Hu, Qiulei Dong
This work is a systematical analysis on the so-called hard class problem in zero-shot learning (ZSL), that is, some unseen classes disproportionally affect the ZSL performances than others, as well as how to remedy the problem by detecting and exploiting hard classes.
no code implementations • 8 Jul 2021 • Shuang Deng, Qiulei Dong, Bo Liu, Zhanyi Hu
The proposed network is iteratively updated with its predicted pseudo labels, where a superpoint generation module is introduced for extracting superpoints from 3D point clouds, and a pseudo-label optimization module is explored for automatically assigning pseudo labels to the unlabeled points under the constraint of the extracted superpoints.
1 code implementation • 7 Jul 2021 • Shuang Deng, Bo Liu, Qiulei Dong, Zhanyi Hu
Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis.
no code implementations • 1 Jul 2021 • Bo Liu, Shuang Deng, Qiulei Dong, Zhanyi Hu
In this work, a language-level Semantics Conditioned framework for 3D Point cloud segmentation, called SeCondPoint, is proposed, where language-level semantics are introduced to condition the modeling of point feature distribution as well as the pseudo-feature generation, and a feature-geometry-based mixup approach is further proposed to facilitate the distribution learning.
1 code implementation • CVPR 2021 • Liu Bo, Qiulei Dong, Zhanyi Hu
Addressing this problem, we first empirically analyze the roles of unseen-class samples with different degrees of hardness in the training process based on the uneven prediction phenomenon found in many ZSL methods, resulting in three observations.
1 code implementation • 22 Oct 2020 • Jinxu Liu, Wei Gao, Zhanyi Hu
Unlike loose coupling approaches and the EKF-based approaches in the literature, we propose an optimization-based visual-inertial SLAM tightly coupled with raw Global Navigation Satellite System (GNSS) measurements, a first attempt of this kind in the literature to our knowledge.
Robotics
no code implementations • 29 Aug 2020 • Bo Liu, Qiulei Dong, Zhanyi Hu
In addition, considering that the visual features from categorization CNNs are generally inconsistent with their semantic features, a simple feature selection strategy is introduced for extracting more compact semantic visual features.
no code implementations • 1 Feb 2020 • Jinxu Liu, Wei Gao, Zhanyi Hu
the extrinsic parameters before the first turning, which is a complement of the existing results of observability analyses.
Robotics
no code implementations • 22 Oct 2019 • Qiulei Dong, Jiayin Sun, Zhanyi Hu
In this work, we investigate this problem by formulating face images as points in a shape-appearance parameter space, and our results demonstrate that: (i) The encoding and decoding of the neuron responses (representations) to face images in CNNs could be achieved under a linear model in the parameter space, in agreement with the recent discovery in primate IT face neurons, but different from the aforementioned perspective on CNNs' face representation with complex image feature encoding; (ii) The linear model for face encoding and decoding in the parameter space could achieve close or even better performances on face recognition and verification than state-of-the-art CNNs, which might provide new lights on the design strategies for face recognition systems; (iii) The neuron responses to face images in CNNs could not be adequately modelled by the axis model, a model recently proposed on face modelling in primate IT cortex.
no code implementations • 6 Jun 2019 • Qiulei Dong, Bo Liu, Zhanyi Hu
Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modelling approach for neural object representation in primate inferotemporal cortex.
no code implementations • 21 Apr 2019 • Xiang Gao, Shuhan Shen, Lingjie Zhu, Tianxin Shi, Zhiheng Wang, Zhanyi Hu
Experimental evaluations on two ancient Chinese architecture datasets demonstrate the effectiveness of our proposed complete scene reconstruction pipeline.
no code implementations • ECCV 2018 • Lingjie Zhu, Shuhan Shen, Xiang Gao, Zhanyi Hu
There are two major steps in our framework: segmentation and building modeling.
no code implementations • 27 Mar 2018 • Lei He, Guanghui Wang, Zhanyi Hu
In order to learn monocular depth by embedding the focal length, we propose a method to generate synthetic varying-focal-length dataset from fixed-focal-length datasets, and a simple and effective method is implemented to fill the holes in the newly generated images.
no code implementations • 23 Mar 2018 • Hainan Cui, Shuhan Shen, Xiang Gao, Zhanyi Hu
The global manner has the advantage of simultaneously estimating all camera poses, but it is usually sensitive to epipolar geometry outliers.
no code implementations • CVPR 2017 • Hainan Cui, Xiang Gao, Shuhan Shen, Zhanyi Hu
In this work, we propose a new hybrid SfM method to tackle the issues of efficiency, accuracy and robustness in a unified framework.
no code implementations • 12 Dec 2016 • Qiulei Dong, Zhanyi Hu
Lehky et al. (Lehky, 2011) provided a statistical analysis on neural responses to object stimuli in primate AIT cortex.
no code implementations • 26 Apr 2016 • Rizhen Qin, Wei Gao, Huarong Xu, Zhanyi Hu
The classification results show that the personality traits "Rule-consciousness" and "Vigilance" can be predicted reliably, and that the traits of females can be predicted more accurately than those of male.
no code implementations • 1 Dec 2015 • Miao Yu, Shuhan Shen, Zhanyi Hu
Through both the splitting and merging, we further propose a dynamic parallel and distributed graph-cuts algorithm with guaranteed convergence to the globally optimal solutions within a predefined number of iterations.