Search Results for author: Yangyan Li

Found 14 papers, 9 papers with code

ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation

1 code implementation ICCV 2021 Jinming Cao, Hanchao Leng, Dani Lischinski, Danny Cohen-Or, Changhe Tu, Yangyan Li

The reason is that the learnt weights for balancing the importance between the shape and base components in ShapeConv become constants in the inference phase, and thus can be fused into the following convolution, resulting in a network that is identical to one with vanilla convolutional layers.

Semantic Segmentation

DO-Conv: Depthwise Over-parameterized Convolutional Layer

1 code implementation22 Jun 2020 Jinming Cao, Yangyan Li, Mingchao Sun, Ying Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen, Changhe Tu

Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization.

Image Classification

GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling

1 code implementation27 May 2020 Zhuoying Wang, Yongtao Wang, Zhi Tang, Yangyan Li, Ying Chen, Haibin Ling, Weisi Lin

Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation.

Pose Estimation Semantic Segmentation

Face Identity Disentanglement via Latent Space Mapping

3 code implementations15 May 2020 Yotam Nitzan, Amit Bermano, Yangyan Li, Daniel Cohen-Or

Learning disentangled representations of data is a fundamental problem in artificial intelligence.


MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion

no code implementations19 Jan 2020 Kaiyu Shan, Yongtao Wang, Zhuoying Wang, TingTing Liang, Zhi Tang, Ying Chen, Yangyan Li

To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone.

Action Recognition

DiDA: Disentangled Synthesis for Domain Adaptation

no code implementations21 May 2018 Jinming Cao, Oren Katzir, Peng Jiang, Dani Lischinski, Danny Cohen-Or, Changhe Tu, Yangyan Li

The key idea is that by learning to separately extract both the common and the domain-specific features, one can synthesize more target domain data with supervision, thereby boosting the domain adaptation performance.

Unsupervised Domain Adaptation

PointCNN: Convolution On $\mathcal{X}$-Transformed Points

8 code implementations NeurIPS 2018 Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen

The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.

 Ranked #1 on 3D Instance Segmentation on S3DIS (mIoU metric)

3D Instance Segmentation 3D Part Segmentation +1

Bundle Optimization for Multi-aspect Embedding

no code implementations29 Mar 2017 Qiong Zeng, Baoquan Chen, Yanir Kleiman, Daniel Cohen-Or, Yangyan Li

Understanding semantic similarity among images is the core of a wide range of computer vision applications.

Image Classification Semantic Similarity +1

A Holistic Approach for Data-Driven Object Cutout

no code implementations18 Aug 2016 Huayong Xu, Yangyan Li, Wenzheng Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen

We show that the resulting P-maps may be used to evaluate how likely a rectangle proposal is to contain an instance of the class, and further process good proposals to produce an accurate object cutout mask.

Cannot find the paper you are looking for? You can Submit a new open access paper.