Search Results for author: Henghui Ding

Found 33 papers, 10 papers with code

A Closer Look at Few-shot Image Generation

no code implementations8 May 2022 Yunqing Zhao, Henghui Ding, Houjing Huang, Ngai-Man Cheung

Informed by our analysis and to slow down the diversity degradation of the target generator during adaptation, our second contribution proposes to apply mutual information (MI) maximization to retain the source domain's rich multi-level diversity information in the target domain generator.

Contrastive Learning Image Generation

Instance-Specific Feature Propagation for Referring Segmentation

no code implementations26 Apr 2022 Chang Liu, Xudong Jiang, Henghui Ding

In this work, we propose a novel framework that simultaneously detects the target-of-interest via feature propagation and generates a fine-grained segmentation mask.

Instance Segmentation Semantic Segmentation

Coarse-to-Fine Feature Mining for Video Semantic Segmentation

1 code implementation7 Apr 2022 Guolei Sun, Yun Liu, Henghui Ding, Thomas Probst, Luc van Gool

To address this problem, we propose a Coarse-to-Fine Feature Mining (CFFM) technique to learn a unified presentation of static contexts and motional contexts.

Frame Semantic Segmentation +1

Flow-Guided Sparse Transformer for Video Deblurring

no code implementations6 Jan 2022 Jing Lin, Yuanhao Cai, Xiaowan Hu, Haoqian Wang, Youliang Yan, Xueyi Zou, Henghui Ding, Yulun Zhang, Radu Timofte, Luc van Gool

Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring.

Deblurring Frame +1

Time-Aware Neighbor Sampling for Temporal Graph Networks

no code implementations18 Dec 2021 Yiwei Wang, Yujun Cai, Yuxuan Liang, Henghui Ding, Changhu Wang, Bryan Hooi

In this work, we propose the TNS (Time-aware Neighbor Sampling) method: TNS learns from temporal information to provide an adaptive receptive neighborhood for every node at any time.

Node Classification

Structure-Aware Label Smoothing for Graph Neural Networks

no code implementations1 Dec 2021 Yiwei Wang, Yujun Cai, Yuxuan Liang, Wei Wang, Henghui Ding, Muhao Chen, Jing Tang, Bryan Hooi

Representing a label distribution as a one-hot vector is a common practice in training node classification models.

Classification Node Classification

Directed Graph Contrastive Learning

1 code implementation NeurIPS 2021 Zekun Tong, Yuxuan Liang, Henghui Ding, Yongxing Dai, Xinke Li, Changhu Wang

However, it is still in its infancy with two concerns: 1) changing the graph structure through data augmentation to generate contrastive views may mislead the message passing scheme, as such graph changing action deprives the intrinsic graph structural information, especially the directional structure in directed graphs; 2) since GCL usually uses predefined contrastive views with hand-picking parameters, it does not take full advantage of the contrastive information provided by data augmentation, resulting in incomplete structure information for models learning.

Contrastive Learning Data Augmentation

Adaptive Data Augmentation on Temporal Graphs

no code implementations NeurIPS 2021 Yiwei Wang, Yujun Cai, Yuxuan Liang, Henghui Ding, Changhu Wang, Siddharth Bhatia, Bryan Hooi

To address this issue, our idea is to transform the temporal graphs using data augmentation (DA) with adaptive magnitudes, so as to effectively augment the input features and preserve the essential semantic information.

Data Augmentation Node Classification

LONG-TAILED RECOGNITION BY LEARNING FROM LATENT CATEGORIES

no code implementations29 Sep 2021 Weide Liu, Zhonghua Wu, Yiming Wang, Henghui Ding, Fayao Liu, Jie Lin, Guosheng Lin

In this work, we argue that there are common latent features between the head and tailed classes that can be used to give better feature representation.

Data Augmentation

Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning

no code implementations ICCV 2021 Chi Zhang, Henghui Ding, Guosheng Lin, Ruibo Li, Changhu Wang, Chunhua Shen

Inspired by the recent success in Automated Machine Learning literature (AutoML), in this paper, we present Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few-shot learning designs.

AutoML Few-Shot Learning

Calibrating Class Activation Maps for Long-Tailed Visual Recognition

no code implementations29 Aug 2021 Chi Zhang, Guosheng Lin, Lvlong Lai, Henghui Ding, Qingyao Wu

First, we present a Class Activation Map Calibration (CAMC) module to improve the learning and prediction of network classifiers, by enforcing network prediction based on important image regions.

Representation Learning

Vision-Language Transformer and Query Generation for Referring Segmentation

1 code implementation ICCV 2021 Henghui Ding, Chang Liu, Suchen Wang, Xudong Jiang

We introduce transformer and multi-head attention to build a network with an encoder-decoder attention mechanism architecture that "queries" the given image with the language expression.

Referring Expression Segmentation

Few-Shot Segmentation with Global and Local Contrastive Learning

1 code implementation11 Aug 2021 Weide Liu, Zhonghua Wu, Henghui Ding, Fayao Liu, Jie Lin, Guosheng Lin

To this end, we first propose a prior extractor to learn the query information from the unlabeled images with our proposed global-local contrastive learning.

Contrastive Learning Semantic Segmentation

M2IOSR: Maximal Mutual Information Open Set Recognition

no code implementations5 Aug 2021 Xin Sun, Henghui Ding, Chi Zhang, Guosheng Lin, Keck-Voon Ling

In this work, we aim to address the challenging task of open set recognition (OSR).

Open Set Learning

Improving Video Instance Segmentation via Temporal Pyramid Routing

1 code implementation28 Jul 2021 Xiangtai Li, Hao He, Henghui Ding, Kuiyuan Yang, Guangliang Cheng, Jianping Shi, Yunhai Tong

Moreover, our approach is a plug-and-play module and can be easily applied to existing instance segmentation methods.

Frame Instance Segmentation +2

Recovering the Unbiased Scene Graphs from the Biased Ones

1 code implementation5 Jul 2021 Meng-Jiun Chiou, Henghui Ding, Hanshu Yan, Changhu Wang, Roger Zimmermann, Jiashi Feng

Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.

Scene Graph Classification Scene Graph Detection +2

Knowledge-aware Deep Framework for Collaborative Skin Lesion Segmentation and Melanoma Recognition

no code implementations7 Jun 2021 XiaoHong Wang, Xudong Jiang, Henghui Ding, Yuqian Zhao, Jun Liu

In this paper, we propose a novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning of two important melanoma diagnosis tasks, i. e., skin lesion segmentation and melanoma recognition.

Lesion Segmentation Skin Lesion Segmentation

MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis

1 code implementation ICCV 2021 Jiaxin Li, Zijian Feng, Qi She, Henghui Ding, Changhu Wang, Gim Hee Lee

In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image.

3D Reconstruction Depth Estimation +1

Towards Enhancing Fine-grained Details for Image Matting

no code implementations22 Jan 2021 Chang Liu, Henghui Ding, Xudong Jiang

In this paper, we argue that recovering these microscopic details relies on low-level but high-definition texture features.

Image Matting

Interaction via Bi-Directional Graph of Semantic Region Affinity for Scene Parsing

no code implementations ICCV 2021 Henghui Ding, HUI ZHANG, Jun Liu, Jiaxin Li, Zijian Feng, Xudong Jiang

In this work, we treat each respective region in an image as a whole, and capture the structure topology as well as the affinity among different regions.

Scene Parsing

Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation

no code implementations ICCV 2021 HUI ZHANG, Henghui Ding

In this work, we present zero-shot semantic segmentation, which aims to identify not only the seen classes contained in training but also the novel classes that have never been seen.

Semantic Segmentation

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

no code implementations ICCV 2021 Yujun Cai, Yiwei Wang, Yiheng Zhu, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Chuanxia Zheng, Sijie Yan, Henghui Ding, Xiaohui Shen, Ding Liu, Nadia Magnenat Thalmann

Notably, by considering this problem as a conditional generation process, we estimate a parametric distribution of the missing regions based on the input conditions, from which to sample and synthesize the full motion series.

motion prediction motion synthesis

Object 6D Pose Estimation with Non-local Attention

no code implementations20 Feb 2020 Jianhan Mei, Henghui Ding, Xudong Jiang

In this paper, we address the challenging task of estimating 6D object pose from a single RGB image.

6D Pose Estimation Object Detection

Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation

no code implementations20 Feb 2020 Xiaohong Wang, Xudong Jiang, Henghui Ding, Jun Liu

Accurate segmentation of skin lesion from dermoscopic images is a crucial part of computer-aided diagnosis of melanoma.

Lesion Segmentation Skin Lesion Segmentation

Semantic Correlation Promoted Shape-Variant Context for Segmentation

no code implementations CVPR 2019 Henghui Ding, Xudong Jiang, Bing Shuai, Ai Qun Liu, Gang Wang

In this way, the proposed network aggregates the context information of a pixel from its semantic-correlated region instead of a predefined fixed region.

Denoising Semantic Segmentation

Boundary-Aware Feature Propagation for Scene Segmentation

1 code implementation ICCV 2019 Henghui Ding, Xudong Jiang, Ai Qun Liu, Nadia Magnenat Thalmann, Gang Wang

Furthermore, we propose a boundary-aware feature propagation (BFP) module to harvest and propagate the local features within their regions isolated by the learned boundaries in the UAG-structured image.

Scene Segmentation

Toward Achieving Robust Low-Level and High-Level Scene Parsing

1 code implementation journal 2019 Bing Shuai, Henghui Ding, Ting Liu, Gang Wang, Xudong Jiang

Furthermore, we introduce a “dense skip” architecture to retain a rich set of low-level information from the pre-trained CNN, which is essential to improve the low-level parsing performance.

Scene Parsing Scene Segmentation

Feature Boosting Network For 3D Pose Estimation

no code implementations15 Jan 2019 Jun Liu, Henghui Ding, Amir Shahroudy, Ling-Yu Duan, Xudong Jiang, Gang Wang, Alex C. Kot

Learning a set of features that are reliable and discriminatively representative of the pose of a hand (or body) part is difficult due to the ambiguities, texture and illumination variation, and self-occlusion in the real application of 3D pose estimation.

3D Hand Pose Estimation 3D Pose Estimation

Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation

1 code implementation CVPR 2018 Henghui Ding, Xudong Jiang, Bing Shuai, Ai Qun Liu, Gang Wang

In this paper, we first propose a novel context contrasted local feature that not only leverages the informative context but also spotlights the local information in contrast to the context.

Scene Segmentation

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