892 citations · 3.1k across the 17 of their papers we have counts for
17 papers
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception
Hongyu Zhou, Zheng Ge, Zeming Li +1
This paper proposes an efficient multi-camera to Bird's-Eye-View (BEV) view transformation method for 3D perception, dubbed MatrixVT. Existing view transformers either suffer from…
Rethinking Learnable Tree Filter for Generic Feature Transform
Lin Song, Yanwei Li, Zhengkai Jiang +5
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces…
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…
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 (…
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…
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ningning Ma, Xiangyu Zhang, Hai-Tao Zheng +1
Currently, the neural network architecture design is mostly guided by the \emph{indirect} metric of computation complexity, i.e., FLOPs. However, the \emph{direct} metric, e.g., sp…
MetaAnchor: Learning to Detect Objects with Customized Anchors
Tong Yang, Xiangyu Zhang, Zeming Li +2
We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks. Unlike many previous detectors model anchors via a predefined manner, in MetaAnch…
CrowdHuman: A Benchmark for Detecting Human in a Crowd
Shuai Shao, Zijian Zhao, Boxun Li +4
Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matter…
DetNet: A Backbone network for Object Detection
Zeming Li, Chao Peng, Gang Yu +3
Recent CNN based object detectors, no matter one-stage methods like YOLO, SSD, and RetinaNe or two-stage detectors like Faster R-CNN, R-FCN and FPN are usually trying to directly f…
ExFuse: Enhancing Feature Fusion for Semantic Segmentation
Zhenli Zhang, Xiangyu Zhang, Chao Peng +2
Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance. In this paper, we fir…
Light-Head R-CNN: In Defense of Two-Stage Object Detector
Zeming Li, Chao Peng, Gang Yu +3
In this paper, we first investigate why typical two-stage methods are not as fast as single-stage, fast detectors like YOLO and SSD. We find that Faster R-CNN and R-FCN perform an…
MegDet: A Large Mini-Batch Object Detector
Chao Peng, Tete Xiao, Zeming Li +5
The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network,…
Channel Pruning for Accelerating Very Deep Neural Networks
Yihui He, Xiangyu Zhang, Jian Sun
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.Given a trained CNN model, we propose an iterative two-step algorithm…
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin +1
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MF…
Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network
Chao Peng, Xiangyu Zhang, Gang Yu +2
One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef-…