892 citations · 2.6k across the 28 of their papers we have counts for
28 papers
End-to-End Human Object Interaction Detection with HOI Transformer
Cheng Zou, Bohan Wang, Yue Hu +8
We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner. Current approaches either decouple HOI task into separated stages of object d…
Fully Convolutional Networks for Panoptic Segmentation
Yanwei Li, Hengshuang Zhao, Xiaojuan Qi +4
In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foregrou…
UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
Kunming Luo, Chuan Wang, Shuaicheng Liu +3
We present an unsupervised learning approach for optical flow estimation by improving the upsampling and learning of pyramid network. We design a self-guided upsample module to tac…
Self-EMD: Self-Supervised Object Detection without ImageNet
Songtao Liu, Zeming Li, Jian Sun
In this paper, we propose a novel self-supervised representation learning method, Self-EMD, for object detection. Our method directly trained on unlabeled non-iconic image dataset…
Joint COCO and Mapillary Workshop at ICCV 2019: COCO Instance Segmentation Challenge Track
Zeming Li, Yuchen Ma, Yukang Chen +2
In this report, we present our object detection/instance segmentation system, MegDetV2, which works in a two-pass fashion, first to detect instances then to obtain segmentation. Ou…
EqCo: Equivalent Rules for Self-supervised Contrastive Learning
Benjin Zhu, Junqiang Huang, Zeming Li +2
In this paper, we propose EqCo (Equivalent Rules for Contrastive Learning) to make self-supervised learning irrelevant to the number of negative samples in the contrastive learning…
Activate or Not: Learning Customized Activation
Ningning Ma, Xiangyu Zhang, Ming Liu +1
We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not. Interestingly, we find Swish, the recent popular NAS-searc…
LabelEnc: A New Intermediate Supervision Method for Object Detection
Miao Hao, Yitao Liu, Xiangyu Zhang +1
In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems. The key idea is to introduce a novel label encodi…
Funnel Activation for Visual Recognition
Ningning Ma, Xiangyu Zhang, Jian Sun
We present a conceptually simple but effective funnel activation for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by ad…
WeightNet: Revisiting the Design Space of Weight Networks
Ningning Ma, Xiangyu Zhang, Jiawei Huang +1
We present a conceptually simple, flexible and effective framework for weight generating networks. Our approach is general that unifies two current distinct and extremely effective…
BorderDet: Border Feature for Dense Object Detection
Han Qiu, Yuchen Ma, Zeming Li +2
Dense object detectors rely on the sliding-window paradigm that predicts the object over a regular grid of image. Meanwhile, the feature maps on the point of the grid are adopted t…
AutoAssign: Differentiable Label Assignment for Dense Object Detection
Benjin Zhu, Jianfeng Wang, Zhengkai Jiang +4
Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledg…
Spherical Motion Dynamics: Learning Dynamics of Neural Network with Normalization, Weight Decay, and SGD
Ruosi Wan, Zhanxing Zhu, Xiangyu Zhang +1
In this work, we comprehensively reveal the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum), named as Spherical Motion Dynamics (…
Attentive Normalization for Conditional Image Generation
Yi Wang, Ying-Cong Chen, Xiangyu Zhang +2
Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled w…
Angle-based Search Space Shrinking for Neural Architecture Search
Yiming Hu, Yuding Liang, Zichao Guo +5
In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for Neural Architecture Search (NAS). Our approach pro…
Learning Dynamic Routing for Semantic Segmentation
Yanwei Li, Lin Song, Yukang Chen +4
Recently, numerous handcrafted and searched networks have been applied for semantic segmentation. However, previous works intend to handle inputs with various scales in pre-defined…
Detection in Crowded Scenes: One Proposal, Multiple Predictions
Xuangeng Chu, Anlin Zheng, Xiangyu Zhang +1
We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal…
Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
Junjie Yan, Ruosi Wan, Xiangyu Zhang +3
Batch Normalization (BN) is one of the most widely used techniques in Deep Learning field. But its performance can awfully degrade with insufficient batch size. This weakness limit…
Content-Aware Unsupervised Deep Homography Estimation
Jirong Zhang, Chuan Wang, Shuaicheng Liu +5
Homography estimation is a basic image alignment method in many applications. It is usually conducted by extracting and matching sparse feature points, which are error-prone in low…
DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
Hanchao Li, Pengfei Xiong, Haoqiang Fan +1
This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints. Our proposed network starts from a single lightweig…
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution
Xuecai Hu, Haoyuan Mu, Xiangyu Zhang +3
Recent research on super-resolution has achieved great success due to the development of deep convolutional neural networks (DCNNs). However, super-resolution of arbitrary scale fa…
Single Path One-Shot Neural Architecture Search with Uniform Sampling
Zichao Guo, Xiangyu Zhang, Haoyuan Mu +4
We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and n…
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
Zechun Liu, Haoyuan Mu, Xiangyu Zhang +4
In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is a…
GridFace: Face Rectification via Learning Local Homography Transformations
Erjin Zhou, Zhimin Cao, Jian Sun
In this paper, we propose a method, called GridFace, to reduce facial geometric variations and improve the recognition performance. Our method rectifies the face by local homograph…