Improving Semantic Segmentation via Self-Training

no code implementations • 30 Apr 2020 • Yi Zhu, Zhongyue Zhang, Chongruo wu, Zhi Zhang, Tong He, Hang Zhang, R. Manmatha, Mu Li, Alexander Smola

In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models.

Domain Generalization Segmentation +1

ResNeSt: Split-Attention Networks

35 code implementations • 19 Apr 2020 • Hang Zhang, Chongruo wu, Zhongyue Zhang, Yi Zhu, Haibin Lin, Zhi Zhang, Yue Sun, Tong He, Jonas Mueller, R. Manmatha, Mu Li, Alexander Smola

It is well known that featuremap attention and multi-path representation are important for visual recognition.

Image Classification Instance Segmentation +3

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

4 code implementations • 9 Jul 2019 • Jian Guo, He He, Tong He, Leonard Lausen, Mu Li, Haibin Lin, Xingjian Shi, Chenguang Wang, Junyuan Xie, Sheng Zha, Aston Zhang, Hang Zhang, Zhi Zhang, Zhongyue Zhang, Shuai Zheng, Yi Zhu

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).

Predicting Retrosynthetic Reaction using Self-Corrected Transformer Neural Networks

1 code implementation • 2 Jul 2019 • Shuangjia Zheng, Jiahua Rao, Zhongyue Zhang, Jun Xu, Yuedong Yang

Synthesis planning is the process of recursively decomposing target molecules into available precursors.

Machine Translation Retrosynthesis +1

Bag of Freebies for Training Object Detection Neural Networks

3 code implementations • 11 Feb 2019 • Zhi Zhang, Tong He, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li

Training heuristics greatly improve various image classification model accuracies~\cite{he2018bag}.

General Classification Image Classification +2

Bag of Tricks for Image Classification with Convolutional Neural Networks

27 code implementations • CVPR 2019 • Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.

Domain Generalization General Classification +4

Context Encoding for Semantic Segmentation

12 code implementations • CVPR 2018 • Hang Zhang, Kristin Dana, Jianping Shi, Zhongyue Zhang, Xiaogang Wang, Ambrish Tyagi, Amit Agrawal

In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps.

Image Classification Segmentation +2

megaman: Manifold Learning with Millions of points

1 code implementation • 9 Mar 2016 • James McQueen, Marina Meila, Jacob VanderPlas, Zhongyue Zhang

Manifold Learning is a class of algorithms seeking a low-dimensional non-linear representation of high-dimensional data.