no code implementations • 28 Sep 2022 • Alex Zhuang, Eddy Zhou, Quanquan Li, Rowan Dempster, Alikasim Budhwani, Mohammad Al-Sharman, Derek Rayside, William Melek
When applied to autonomous vehicle settings, action recognition can help enrich an environment model's understanding of the world and improve plans for future action.
1 code implementation • CVPR 2021 • Gang Zhang, Xin Lu, Jingru Tan, Jianmin Li, Zhaoxiang Zhang, Quanquan Li, Xiaolin Hu
In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner.
no code implementations • 31 Mar 2021 • Jiangfan Han, Mengya Gao, Yujie Wang, Quanquan Li, Hongsheng Li, Xiaogang Wang
To solve this problem, in this paper, we propose a novel student-dependent distillation method, knowledge consistent distillation, which makes teacher's knowledge more consistent with the student and provides the best suitable knowledge to different student networks for distillation.
no code implementations • 30 Mar 2021 • Shaopeng Guo, Yujie Wang, Kun Yuan, Quanquan Li
In this paper we propose a novel network adaption method called Differentiable Network Adaption (DNA), which can adapt an existing network to a specific computation budget by adjusting the width and depth in a differentiable manner.
no code implementations • ICCV 2021 • Kun Yuan, Quanquan Li, Shaopeng Guo, Dapeng Chen, Aojun Zhou, Fengwei Yu, Ziwei Liu
A standard practice of deploying deep neural networks is to apply the same architecture to all the input instances.
no code implementations • 1 Jan 2021 • Yuxin Yue, Quanquan Li, Yujie Wang
Many commonly-used detection frameworks aim to handle the multi-scale object detection problem.
2 code implementations • CVPR 2021 • Jingru Tan, Xin Lu, Gang Zhang, Changqing Yin, Quanquan Li
To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally.
Ranked #9 on Instance Segmentation on LVIS v1.0 val
no code implementations • 2 Oct 2020 • Kun Yuan, Quanquan Li, Dapeng Chen, Aojun Zhou, Junjie Yan
To facilitate the training, we represent the network connectivity of each sample in an adjacency matrix.
no code implementations • ECCV 2020 • Xin Lu, Quanquan Li, Buyu Li, Junjie Yan
In this paper, we propose MimicDet, a novel and efficient framework to train a one-stage detector by directly mimic the two-stage features, aiming to bridge the accuracy gap between one-stage and two-stage detectors.
no code implementations • 3 Sep 2020 • Jingru Tan, Gang Zhang, Hanming Deng, Changbao Wang, Lewei Lu, Quanquan Li, Jifeng Dai
This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020.
Ranked #1 on Instance Segmentation on LVIS v1.0 test-dev
no code implementations • ECCV 2020 • Kun Yuan, Quanquan Li, Jing Shao, Junjie Yan
In this paper, we attempt to optimize the connectivity in neural networks.
1 code implementation • CVPR 2020 • Shaopeng Guo, Yujie Wang, Quanquan Li, Junjie Yan
In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process.
1 code implementation • CVPR 2020 • Jingru Tan, Changbao Wang, Buyu Li, Quanquan Li, Wanli Ouyang, Changqing Yin, Junjie Yan
Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories.
Ranked #15 on Long-tail Learning on CIFAR-10-LT (ρ=10)
no code implementations • 21 Feb 2020 • Mengya Gao, Yujun Shen, Quanquan Li, Chen Change Loy
Knowledge distillation (KD) is one of the most potent ways for model compression.
no code implementations • 12 Nov 2019 • Jingru Tan, Changbao Wang, Quanquan Li, Junjie Yan
Recent object detection and instance segmentation tasks mainly focus on datasets with a relatively small set of categories, e. g. Pascal VOC with 20 classes and COCO with 80 classes.
no code implementations • 25 Sep 2019 • Kun Yuan, Quanquan Li, Yucong Zhou, Jing Shao, Junjie Yan
Seeking effective networks has become one of the most crucial and practical areas in deep learning.
2 code implementations • 13 Jun 2019 • Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, Junjie Yan
Grid R-CNN is a well-performed objection detection framework.
no code implementations • ICLR 2019 • Wei Gao, Yi Wei, Quanquan Li, Hongwei Qin, Wanli Ouyang, Junjie Yan
Hints can improve the performance of student model by transferring knowledge from teacher model.
no code implementations • 19 Feb 2019 • Chen Change Loy, Dahua Lin, Wanli Ouyang, Yuanjun Xiong, Shuo Yang, Qingqiu Huang, Dongzhan Zhou, Wei Xia, Quanquan Li, Ping Luo, Junjie Yan, Jian-Feng Wang, Zuoxin Li, Ye Yuan, Boxun Li, Shuai Shao, Gang Yu, Fangyun Wei, Xiang Ming, Dong Chen, Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li, Hongkai Zhang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, Wu Liu, Boyan Zhou, Huaxiong Li, Peng Cheng, Tao Mei, Artem Kukharenko, Artem Vasenin, Nikolay Sergievskiy, Hua Yang, Liangqi Li, Qiling Xu, Yuan Hong, Lin Chen, Mingjun Sun, Yirong Mao, Shiying Luo, Yongjun Li, Ruiping Wang, Qiaokang Xie, Ziyang Wu, Lei Lu, Yiheng Liu, Wengang Zhou
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
1 code implementation • 5 Dec 2018 • Mengya Gao, Yujun Shen, Quanquan Li, Junjie Yan, Liang Wan, Dahua Lin, Chen Change Loy, Xiaoou Tang
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
2 code implementations • CVPR 2019 • Xin Lu, Buyu Li, Yuxin Yue, Quanquan Li, Junjie Yan
This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.
Ranked #150 on Object Detection on COCO minival
no code implementations • CVPR 2017 • Quanquan Li, Shengying Jin, Junjie Yan
More specifically, we conduct a mimic method for the features sampled from the entire feature map and use a transform layer to map features from the small network onto the same dimension of the large network.
no code implementations • 19 Oct 2016 • Fengwei Yu, Wenbo Li, Quanquan Li, Yu Liu, Xiaohua Shi, Junjie Yan
In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting.