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.
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.
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.
A standard practice of deploying deep neural networks is to apply the same architecture to all the input instances.
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 #2 on Instance Segmentation on LVIS v1.0 val
To facilitate the training, we represent the network connectivity of each sample in an adjacency matrix.
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.
This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020.
Ranked #1 on Instance Segmentation on LVIS v1.0 test-dev
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.
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.
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.
Seeking effective networks has become one of the most crucial and practical areas in deep learning.
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.
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.
Ranked #113 on Object Detection on COCO minival
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.
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.