• Publications
  • Influence
Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network
TLDR
We propose a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation and achieve state-of-art performance. Expand
  • 578
  • 75
  • PDF
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
TLDR
We propose the Bilateral Segmentation Network (BiSeNet) with two parts: Spatial Path (SP) and Context Path (CP). Expand
  • 314
  • 60
  • PDF
Light-Head R-CNN: In Defense of Two-Stage Object Detector
TLDR
We propose a new two-stage detector, Light-Head R-CNN, which outperforms state-of-art object detectors on COCO while keeping time efficiency. Expand
  • 157
  • 39
  • PDF
Learning a Discriminative Feature Network for Semantic Segmentation
TLDR
We propose a Discriminative Feature Network (DFN), which contains two sub-networks: Smooth Network and Border Network. Expand
  • 271
  • 28
  • PDF
MegDet: A Large Mini-Batch Object Detector
  • Chao Peng, Tete Xiao, +5 authors Jian Sun
  • Computer Science
  • IEEE/CVF Conference on Computer Vision and…
  • 20 November 2017
TLDR
We propose a Large Mini-Batch Object Detector (MegDet) to enable the training with a large minibatch size up to 256, so that we can effectively utilize at most 128 GPUs to significantly shorten the training time. Expand
  • 164
  • 18
  • PDF
DetNet: A Backbone network for Object Detection
TLDR
In this paper, we propose DetNet, which is a novel backbone designed for object detection. Expand
  • 99
  • 16
  • PDF
DetNet: Design Backbone for Object Detection
TLDR
We propose DetNet, which is a novel backbone network specifically designed for the task of object detection. Expand
  • 73
  • 6
  • PDF
Electronic Nose Feature Extraction Methods: A Review
TLDR
Many research groups in academia and industry are focusing on the performance improvement of electronic nose (E-nose) systems mainly involving three optimizations, which are sensitive material selection and sensor array optimization, enhanced feature extraction methods and pattern recognition method selection. Expand
  • 82
  • 5
  • PDF
An End-To-End Network for Panoptic Segmentation
TLDR
We propose a novel end-to-end Occlusion Aware Network (OANet) for panoptic segmentation, which can efficiently and effectively predict both the instance and stuff segmentation in a single network. Expand
  • 38
  • 4
  • PDF
Dynamic bin packing with unit fraction items revisited
TLDR
We study the problem of dynamic bin packing with unit fraction items. Expand
  • 16
  • 4