1 code implementation • 6 Mar 2023 • Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan
We present MotionVideoGAN, a novel video generator synthesizing videos based on the motion space learned by pre-trained image pair generators.
1 code implementation • 8 Feb 2023 • Kun Song, Yuchen Wu, Jiansheng Chen, Tianyu Hu, Huimin Ma
Due to the scarcity of available data, deep learning does not perform well on few-shot learning tasks.
no code implementations • 17 Jan 2023 • Yuchen Wu, Kun Song, Fangzheng Zhao, Jiansheng Chen, Huimin Ma
Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a challenging cross-modal retrieval task.
no code implementations • 7 Nov 2022 • Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan
Then we fine-tune DDPMs pre-trained on large source domains to solve the overfitting problem when training data is limited.
no code implementations • 27 Oct 2022 • Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan
It strengthens global image discrimination and guides adapted GANs to preserve more information learned from source domains for higher image quality.
1 code implementation • NeurIPS 2021 • Jiayu Chen, Yuanxin Zhang, Yuanfan Xu, Huimin Ma, Huazhong Yang, Jiaming Song, Yu Wang, Yi Wu
We motivate our paradigm through a variational perspective, where the learning objective can be decomposed into two terms: task learning on the current task distribution, and curriculum update to a new task distribution.
no code implementations • 11 May 2021 • Xi Li, Meng Cao, Yingying Tang, Scott Johnston, Zhendong Hong, Huimin Ma, Jiulong Shan
Inspired by the observation that audiences have different visual preferences on foreground and background objects, we for the first time propose to use saliency masks in the evaluation processes of the task of video frame interpolation.
no code implementations • ICCV 2021 • Cheng Yu, Jiansheng Chen, Youze Xue, Yuyang Liu, Weitao Wan, Jiayu Bao, Huimin Ma
Physical-world adversarial attacks based on universal adversarial patches have been proved to be able to mislead deep convolutional neural networks (CNNs), exposing the vulnerability of real-world visual classification systems based on CNNs.
no code implementations • 21 May 2020 • Xi Li, Huimin Ma, Hongbing Ma, Yidong Wang
In order to solve this problem, the research proposes an unsupervised foreground segmentation method based on semantic-apparent feature fusion (SAFF).
no code implementations • 10 Mar 2020 • Xi Li, Huimin Ma, Sheng Yi, Yanxian Chen
Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
no code implementations • 19 Feb 2020 • Xiang Wang, Sifei Liu, Huimin Ma, Ming-Hsuan Yang
In this paper, we propose an iterative algorithm to learn such pairwise relations, which consists of two branches, a unary segmentation network which learns the label probabilities for each pixel, and a pairwise affinity network which learns affinity matrix and refines the probability map generated from the unary network.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
no code implementations • 27 Nov 2019 • Ruiqi Lu, Huimin Ma
Pedestrian detection in the crowd is a challenging task because of intra-class occlusion.
no code implementations • 26 Nov 2019 • Ruiqi Lu, Huimin Ma
Training a robust classifier and an accurate box regressor are difficult for occluded pedestrian detection.
no code implementations • 26 Nov 2019 • Sheng Yi, Xi Li, Huimin Ma
To solve this problem, we added the box regression module to the weakly supervised object detection network and proposed a proposal scoring network (PSNet) to supervise it.
Ranked #16 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
no code implementations • 9 May 2019 • Xiaoqin Zhang, Yunfei Li, Huimin Ma, Xiong Luo
Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms.
no code implementations • CVPR 2018 • Xiang Wang, ShaoDi You, Xi Li, Huimin Ma
Then in the top-down step, the refined object regions are used as supervision to train the segmentation network and to predict object masks.
General Classification
Weakly supervised Semantic Segmentation
+1
no code implementations • 8 May 2018 • Dong Zhou, Huimin Ma, Yuhan Dong
To overcome this challenge, we propose a novel method that combines both the cognition-driven model and the data-driven model.
no code implementations • 31 Jan 2018 • Xiaoqin Zhang, Huimin Ma
We apply our method to two of the typical actor-critic reinforcement learning algorithms, DDPG and ACER, and demonstrate with experiments that our method not only outperforms the RL algorithms without pretraining process, but also is more simulation efficient.
no code implementations • ICCV 2017 • Zhichen Zhao, Huimin Ma, ShaoDi You
Second, for each body parts, a Part Action Res-Net is used to predict semantic body part actions.
3 code implementations • CVPR 2017 • Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia
We encode the sparse 3D point cloud with a compact multi-view representation.
no code implementations • 29 Aug 2016 • Xiang Wang, Huimin Ma, Xiaozhi Chen, ShaoDi You
In this paper, we propose a novel edge preserving and multi-scale contextual neural network for salient object detection.
no code implementations • 27 Aug 2016 • Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Huimin Ma, Sanja Fidler, Raquel Urtasun
We then exploit a CNN on top of these proposals to perform object detection.
no code implementations • CVPR 2016 • Xiaozhi Chen, Kaustav Kundu, Ziyu Zhang, Huimin Ma, Sanja Fidler, Raquel Urtasun
The focus of this paper is on proposal generation.
Ranked #8 on
Vehicle Pose Estimation
on KITTI Cars Hard
no code implementations • NeurIPS 2015 • Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Andrew G. Berneshawi, Huimin Ma, Sanja Fidler, Raquel Urtasun
The goal of this paper is to generate high-quality 3D object proposals in the context of autonomous driving.
Ranked #10 on
Vehicle Pose Estimation
on KITTI Cars Hard
no code implementations • CVPR 2015 • Xiaozhi Chen, Huimin Ma, Xiang Wang, Zhichen Zhao
Based on the characteristics of superpixel tightness distribution, we propose an effective method, namely multi-thresholding straddling expansion (MTSE) to reduce localization bias via fast diversification.