Search Results for author: Wenjun Zeng

Found 30 papers, 10 papers with code

WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation

no code implementations29 Sep 2021 Namyup Kim, Taeyoung Son, Cuiling Lan, Wenjun Zeng, Suha Kwak

We also present a method which injects the style representation of the web-crawled data into the source domain on-the-fly during training, which enables the network to experience images of diverse styles with reliable labels for effective training.

Domain Generalization Semantic Segmentation

Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration

1 code implementation12 Sep 2021 Chuanxin Tang, Chong Luo, Zhiyuan Zhao, Dacheng Yin, Yucheng Zhao, Wenjun Zeng

Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript.

speech editing Voice Conversion

A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP

no code implementations30 Aug 2021 Yucheng Zhao, Guangting Wang, Chuanxin Tang, Chong Luo, Wenjun Zeng, Zheng-Jun Zha

Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision.

Self-Supervised Visual Representations Learning by Contrastive Mask Prediction

no code implementations ICCV 2021 Yucheng Zhao, Guangting Wang, Chong Luo, Wenjun Zeng, Zheng-Jun Zha

In this paper, we propose a novel contrastive mask prediction (CMP) task for visual representation learning and design a mask contrast (MaskCo) framework to implement the idea.

Representation Learning Self-Supervised Learning

VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild

no code implementations5 Aug 2021 Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenyu Liu, Wenjun Zeng

We estimate 3D poses from the voxel representation by predicting whether each voxel contains a particular body joint.

3D Human Pose Estimation 3D Pose Estimation

Markov Decision Process modeled with Bandits for Sequential Decision Making in Linear-flow

no code implementations1 Jul 2021 Wenjun Zeng, Yi Liu

In membership/subscriber acquisition and retention, we sometimes need to recommend marketing content for multiple pages in sequence.

Decision Making Q-Learning

ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation

no code implementations21 Jun 2021 Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhibo Chen

We study what features should be aligned across domains and propose to make the domain alignment proactively serve classification by performing feature decomposition and alignment under the guidance of the prior knowledge induced from the classification taskitself.

Classification Unsupervised Domain Adaptation

PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning

no code implementations8 Jun 2021 Tao Yu, Cuiling Lan, Wenjun Zeng, Mingxiao Feng, Zhibo Chen

In this work, we propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning.

Representation Learning

Understanding Mobile GUI: from Pixel-Words to Screen-Sentences

no code implementations25 May 2021 Jingwen Fu, Xiaoyi Zhang, Yuwang Wang, Wenjun Zeng, Sam Yang, Grayson Hilliard

A dataset, RICO-PW, of screenshots with Pixel-Words annotations is built based on the public RICO dataset, which will be released to help to address the lack of high-quality training data in this area.

Unsupervised Visual Representation Learning by Tracking Patches in Video

1 code implementation CVPR 2021 Guangting Wang, Yizhou Zhou, Chong Luo, Wenxuan Xie, Wenjun Zeng, Zhiwei Xiong

The proxy task is to estimate the position and size of the image patch in a sequence of video frames, given only the target bounding box in the first frame.

Action Classification Action Recognition +1

S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation

1 code implementation CVPR 2021 Xiaotian Chen, Yuwang Wang, Xuejin Chen, Wenjun Zeng

S2R-DepthNet consists of: a) a Structure Extraction (STE) module which extracts a domaininvariant structural representation from an image by disentangling the image into domain-invariant structure and domain-specific style components, b) a Depth-specific Attention (DSA) module, which learns task-specific knowledge to suppress depth-irrelevant structures for better depth estimation and generalization, and c) a depth prediction module (DP) to predict depth from the depth-specific representation.

Domain Generalization Monocular Depth Estimation +1

Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification

no code implementations25 Mar 2021 Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Quanzeng You, Zicheng Liu, Kecheng Zheng, Zhibo Chen

Each recomposed feature, obtained based on the domain-invariant feature (which enables a reliable inheritance of identity) and an enhancement from a domain specific feature (which enables the approximation of real distributions), is thus an "ideal" augmentation.

Domain Adaptive Person Re-Identification Person Re-Identification

MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation

no code implementations CVPR 2021 Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhibo Chen

For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics.

Classification General Classification +4

Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation

no code implementations ICCV 2021 Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen

Many unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap, where a feature extractor is trained to fool a domain discriminator in order to have aligned feature distributions.

Unsupervised Domain Adaptation

Generalizing to Unseen Domains: A Survey on Domain Generalization

no code implementations2 Mar 2021 Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Wenjun Zeng, Tao Qin

Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain.

Domain Generalization Representation Learning

Do Generative Models Know Disentanglement? Contrastive Learning is All You Need

1 code implementation21 Feb 2021 Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng

DisCo consists of: (i) a Navigator providing traversal directions in the latent space, and (ii) a $\Delta$-Contrastor composed of two shared-weight Encoders, which encode image pairs along these directions to disentangled representations respectively, and a difference operator to map the encoded representations to the Variation Space.

Contrastive Learning

Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement

1 code implementation21 Feb 2021 Xuanchi Ren, Tao Yang, Yuwang Wang, Wenjun Zeng

From the unsupervised disentanglement perspective, we rethink content and style and propose a formulation for unsupervised C-S disentanglement based on our assumption that different factors are of different importance and popularity for image reconstruction, which serves as a data bias.

3D Reconstruction Affine Transformation +3

GroupifyVAE: from Group-based Definition to VAE-based Unsupervised Representation Disentanglement

no code implementations20 Feb 2021 Tao Yang, Xuanchi Ren, Yuwang Wang, Wenjun Zeng, Nanning Zheng, Pengju Ren

The key idea of the state-of-the-art VAE-based unsupervised representation disentanglement methods is to minimize the total correlation of the latent variable distributions.

AttributeNet: Attribute Enhanced Vehicle Re-Identification

no code implementations7 Feb 2021 Rodolfo Quispe, Cuiling Lan, Wenjun Zeng, Helio Pedrini

Vehicle Re-Identification (V-ReID) is a critical task that associates the same vehicle across images from different camera viewpoints.

Vehicle Re-Identification

VAE^2: Preventing Posterior Collapse of Variational Video Predictions in the Wild

no code implementations28 Jan 2021 Yizhou Zhou, Chong Luo, Xiaoyan Sun, Zheng-Jun Zha, Wenjun Zeng

We believe that VAE$^2$ is also applicable to other stochastic sequence prediction problems where training data are lack of stochasticity.

Video Prediction

Style Normalization and Restitution for Domain Generalization and Adaptation

1 code implementation3 Jan 2021 Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen

In this paper, we design a novel Style Normalization and Restitution module (SNR) to simultaneously ensure both high generalization and discrimination capability of the networks.

Domain Generalization Object Detection +2

Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification

1 code implementation16 Dec 2020 Kecheng Zheng, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang, Zheng-Jun Zha

Based on this finding, we propose to exploit the uncertainty (measured by consistency levels) to evaluate the reliability of the pseudo-label of a sample and incorporate the uncertainty to re-weight its contribution within various ReID losses, including the identity (ID) classification loss per sample, the triplet loss, and the contrastive loss.

Domain Adaptive Person Re-Identification Person Re-Identification +1

An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation

1 code implementation ICCV 2021 Rongchang Xie, Chunyu Wang, Wenjun Zeng, Yizhou Wang

The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for images under different augmentations.

Pose Estimation Semi-Supervised Human Pose Estimation

Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric

1 code implementation23 Nov 2020 Zheng Wang, Xin Yuan, Toshihiko Yamasaki, Yutian Lin, Xin Xu, Wenjun Zeng

In essence, current re-ID overemphasizes the importance of retrieval but underemphasizes that of verification, \textit{i. e.}, all returned images are considered as the target.

Image Retrieval

AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild

2 code implementations26 Oct 2020 Zhe Zhang, Chunyu Wang, Weichao Qiu, Wenhu Qin, Wenjun Zeng

To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views.

Pose Estimation

Uncertainty-Aware Few-Shot Image Classification

no code implementations9 Oct 2020 Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Zhibo Chen, Shih-Fu Chang

In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization.

Classification Few-Shot Image Classification +2

FPCR-Net: Feature Pyramidal Correlation and Residual Reconstruction for Semi-supervised Optical Flow Estimation

no code implementations17 Jan 2020 Xiaolin Song, Yuyang Zhao, Jingyu Yang, Cuiling Lan, Wenjun Zeng

To exploit such flexible and comprehensive information, we propose a semi-supervised Feature Pyramidal Correlation and Residual Reconstruction Network (FPCR-Net) for optical flow estimation from frame pairs.

Optical Flow Estimation

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