Search Results for author: Dong Huang

Found 48 papers, 24 papers with code

Zero-shot Model Diagnosis

no code implementations27 Mar 2023 Jinqi Luo, Zhaoning Wang, Chen Henry Wu, Dong Huang, Fernando de la Torre

Extensive experiments demonstrate that our method is capable of producing counterfactual images and offering sensitivity analysis for model diagnosis without the need for a test set.


Semantic Image Attack for Visual Model Diagnosis

no code implementations23 Mar 2023 Jinqi Luo, Zhaoning Wang, Chen Henry Wu, Dong Huang, Fernando de la Torre

Rather than relying on a carefully designed test set to assess ML models' failures, fairness, or robustness, this paper proposes Semantic Image Attack (SIA), a method based on the adversarial attack that provides semantic adversarial images to allow model diagnosis, interpretability, and robustness.

Adversarial Attack Fairness +1

Heterogeneous Tri-stream Clustering Network

1 code implementation11 Jan 2023 Xiaozhi Deng, Dong Huang, Chang-Dong Wang

Contrastive deep clustering has recently gained significant attention with its ability of joint contrastive learning and clustering via deep neural networks.

Contrastive Learning Deep Clustering

DensePose From WiFi

no code implementations31 Dec 2022 Jiaqi Geng, Dong Huang, Fernando de la Torre

Advances in computer vision and machine learning techniques have led to significant development in 2D and 3D human pose estimation from RGB cameras, LiDAR, and radars.

3D Human Pose Estimation Body Detection +1

Deep Temporal Contrastive Clustering

no code implementations29 Dec 2022 Ying Zhong, Dong Huang, Chang-Dong Wang

Recently the deep learning has shown its advantage in representation learning and clustering for time series data.

Contrastive Learning Representation Learning +1

Efficient Multi-view Clustering via Unified and Discrete Bipartite Graph Learning

1 code implementation9 Sep 2022 Si-Guo Fang, Dong Huang, Xiao-Sha Cai, Chang-Dong Wang, Chaobo He, Yong Tang

By simultaneously formulating the view-specific bipartite graph learning, the view-consensus bipartite graph learning, and the discrete cluster structure learning into a unified objective function, an efficient minimization algorithm is then designed to tackle this optimization problem and directly achieve a discrete clustering solution without requiring additional partitioning, which notably has linear time complexity in data size.

Graph Learning

Adaptively-weighted Integral Space for Fast Multiview Clustering

no code implementations25 Aug 2022 Man-Sheng Chen, Tuo Liu, Chang-Dong Wang, Dong Huang, Jian-Huang Lai

In view of this, we propose an Adaptively-weighted Integral Space for Fast Multiview Clustering (AIMC) with nearly linear complexity.

Multiview Clustering

Two Heads are Better than One: Robust Learning Meets Multi-branch Models

1 code implementation17 Aug 2022 Dong Huang, Qingwen Bu, Yuhao QING, Haowen Pi, Sen Wang, Heming Cui

Compared to all methods that do not use additional data for training, our models achieve 67. 3% and 41. 5% robust accuracy on CIFAR-10 and CIFAR-100 (improving upon the state-of-the-art by +7. 23% and +9. 07%).

Adversarial Robustness Philosophy

Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks

no code implementations14 Jul 2022 Yuanku Xu, Dong Huang, Chang-Dong Wang, Jian-Huang Lai

Specifically, with two random augmentations performed on each image, the backbone network with two weight-sharing views is utilized to learn the representations for the augmented samples, which are then fed to ISM and JC-SLIM for instance-level and cluster-level contrastive learning, respectively.

Contrastive Learning Deep Clustering +1

Vision Transformer for Contrastive Clustering

1 code implementation26 Jun 2022 Hua-Bao Ling, Bowen Zhu, Dong Huang, Ding-Hua Chen, Chang-Dong Wang, Jian-Huang Lai

Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning.

Contrastive Learning Deep Clustering +3

Strongly Augmented Contrastive Clustering

1 code implementation1 Jun 2022 Xiaozhi Deng, Dong Huang, Ding-Hua Chen, Chang-Dong Wang, Jian-Huang Lai

In this paper, we present an end-to-end deep clustering approach termed Strongly Augmented Contrastive Clustering (SACC), which extends the conventional two-augmentation-view paradigm to multiple views and jointly leverages strong and weak augmentations for strengthened deep clustering.

Contrastive Learning Deep Clustering +1

DeepCluE: Enhanced Image Clustering via Multi-layer Ensembles in Deep Neural Networks

no code implementations1 Jun 2022 Dong Huang, Ding-Hua Chen, Xiangji Chen, Chang-Dong Wang, Jian-Huang Lai

In light of this, this paper presents a Deep Clustering via Ensembles (DeepCluE) approach, which bridges the gap between deep clustering and ensemble clustering by harnessing the power of multiple layers in deep neural networks.

Contrastive Learning Deep Clustering +1

Joint Multi-view Unsupervised Feature Selection and Graph Learning

no code implementations18 Apr 2022 Si-Guo Fang, Dong Huang, Chang-Dong Wang, Yong Tang

Second, they often learn the similarity structure by either global structure learning or local structure learning, lacking the capability of graph learning with both global and local structural awareness.

Graph Learning

The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization

1 code implementation9 Apr 2022 Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee, Eric P. Xing

Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.

BIG-bench Machine Learning Domain Generalization

Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicity

1 code implementation22 Mar 2022 Dong Huang, Chang-Dong Wang, Jian-Huang Lai

Then, a set of diversified base clusterings for different view groups are obtained via fast graph partitioning, which are further formulated into a unified bipartite graph for final clustering in the late-stage fusion.

graph partitioning

Seeking Commonness and Inconsistencies: A Jointly Smoothed Approach to Multi-view Subspace Clustering

1 code implementation15 Mar 2022 Xiaosha Cai, Dong Huang, Guang-Yu Zhang, Chang-Dong Wang

Second, many of them overlook the local structures of multiple views and cannot jointly leverage multiple local structures to enhance the subspace representation learning.

Multi-view Subspace Clustering Representation Learning

The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization

no code implementations CVPR 2022 Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee, Eric P. Xing

Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.

BIG-bench Machine Learning Domain Generalization

You Can Wash Better: Daily Handwashing Assessment with Smartwatches

no code implementations9 Dec 2021 Fei Wang, Xilei Wu, Xin Wang, Jianlei Chi, Jingang Shi, Dong Huang

We propose UWash, an intelligent solution upon smartwatches, to assess handwashing for the purpose of raising users' awareness and cultivating habits in high-quality handwashing.

Gesture Recognition Semantic Segmentation

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation

1 code implementation CVPR 2022 Zechun Liu, Kwang-Ting Cheng, Dong Huang, Eric Xing, Zhiqiang Shen

The nonuniform quantization strategy for compressing neural networks usually achieves better performance than its counterpart, i. e., uniform strategy, due to its superior representational capacity.


Elaborative Rehearsal for Zero-shot Action Recognition

1 code implementation ICCV 2021 ShiZhe Chen, Dong Huang

However, due to the complexity and diversity of actions, it remains challenging to semantically represent action classes and transfer knowledge from seen data.

Action Recognition Few-Shot Learning +3

Polarized Self-Attention: Towards High-quality Pixel-wise Regression

5 code implementations arXiv preprint 2021 Huajun Liu, Fuqiang Liu, Xinyi Fan, Dong Huang

Pixel-wise regression is probably the most common problem in fine-grained computer vision tasks, such as estimating keypoint heatmaps and segmentation masks.

Ranked #2 on Semantic Segmentation on Cityscapes val (using extra training data)

Keypoint Detection regression +1

How Do Adam and Training Strategies Help BNNs Optimization?

no code implementations21 Jun 2021 Zechun Liu, Zhiqiang Shen, Shichao Li, Koen Helwegen, Dong Huang, Kwang-Ting Cheng

We show the regularization effect of second-order momentum in Adam is crucial to revitalize the weights that are dead due to the activation saturation in BNNs.

Large Norms of CNN Layers Do Not Hurt Adversarial Robustness

1 code implementation17 Sep 2020 Youwei Liang, Dong Huang

Since the Lipschitz properties of convolutional neural networks (CNNs) are widely considered to be related to adversarial robustness, we theoretically characterize the $\ell_1$ norm and $\ell_\infty$ norm of 2D multi-channel convolutional layers and provide efficient methods to compute the exact $\ell_1$ norm and $\ell_\infty$ norm.

Adversarial Robustness

Multi-view Graph Learning by Joint Modeling of Consistency and Inconsistency

2 code implementations24 Aug 2020 Youwei Liang, Dong Huang, Chang-Dong Wang, Philip S. Yu

To overcome this limitation, we propose a new multi-view graph learning framework, which for the first time simultaneously and explicitly models multi-view consistency and multi-view inconsistency in a unified objective function, through which the consistent and inconsistent parts of each single-view graph as well as the unified graph that fuses the consistent parts can be iteratively learned.

Graph Learning

Self-Challenging Improves Cross-Domain Generalization

8 code implementations ECCV 2020 Zeyi Huang, Haohan Wang, Eric P. Xing, Dong Huang

We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data.

Domain Generalization Image Classification

Multiple Object Tracking by Flowing and Fusing

no code implementations30 Jan 2020 Jimuyang Zhang, Sanping Zhou, Xin Chang, Fangbin Wan, Jinjun Wang, Yang Wu, Dong Huang

Most of Multiple Object Tracking (MOT) approaches compute individual target features for two subtasks: estimating target-wise motions and conducting pair-wise Re-Identification (Re-ID).

Multiple Object Tracking object-detection +1

Multiple Anchor Learning for Visual Object Detection

3 code implementations CVPR 2020 Wei Ke, Tianliang Zhang, Zeyi Huang, Qixiang Ye, Jianzhuang Liu, Dong Huang

In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector.

General Classification Multiple Instance Learning +2

Frame-wise Motion and Appearance for Real-time Multiple Object Tracking

no code implementations6 May 2019 Jimuyang Zhang, Sanping Zhou, Jinjun Wang, Dong Huang

The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames.

Association Multiple Object Tracking

Cutting Down Training Memory by Re-fowarding

no code implementations ICLR 2019 Jianwei Feng, Dong Huang

Our approach automatically finds a subset of vertices in a DNN computation graph, and stores tensors only at these vertices during the first forward.

Temporal Unet: Sample Level Human Action Recognition using WiFi

1 code implementation19 Apr 2019 Fei Wang, Yunpeng Song, Jimuyang Zhang, Jinsong Han, Dong Huang

In this task, every WiFi distortion sample in the whole series should be categorized into one action, which is a critical technique in precise action localization, continuous action segmentation, and real-time action recognition.

Action Recognition Action Segmentation +3

Can WiFi Estimate Person Pose?

1 code implementation30 Mar 2019 Fei Wang, Stanislav Panev, Ziyi Dai, Jinsong Han, Dong Huang

In this paper We try to answer this question by exploring the ability of WiFi on estimating single person pose.

3D Human Pose Estimation General Classification +2

Person-in-WiFi: Fine-grained Person Perception using WiFi

1 code implementation ICCV 2019 Fei Wang, Sanping Zhou, Stanislav Panev, Jinsong Han, Dong Huang

Fine-grained person perception such as body segmentation and pose estimation has been achieved with many 2D and 3D sensors such as RGB/depth cameras, radars (e. g., RF-Pose) and LiDARs.

RF-based Pose Estimation

SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection

1 code implementation29 Mar 2019 Sanping Zhou, Jimuyang Zhang, Jinjun Wang, Fei Wang, Dong Huang

In this paper, we propose a simple yet effective Siamese Edge-Enhancement Network (SE2Net) to preserve the edge structure for salient object detection.

object-detection RGB Salient Object Detection +1

Improving Object Detection with Inverted Attention

1 code implementation28 Mar 2019 Zeyi Huang, Wei Ke, Dong Huang

Our approach (1) operates along both the spatial and channels dimensions of the feature maps; (2) requires no extra training on hard samples, no extra network parameters for attention estimation, and no testing overheads.

object-detection Object Detection

Enhanced Ensemble Clustering via Fast Propagation of Cluster-wise Similarities

no code implementations30 Oct 2018 Dong Huang, Chang-Dong Wang, Hongxing Peng, Jian-Huang Lai, Chee-Keong Kwoh

Upon the constructed graph, a transition probability matrix is defined, based on which the random walk process is conducted to propagate the graph structural information.


Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs

1 code implementation CVPR 2021 Jianwei Feng, Dong Huang

In this paper, we present theories and optimal algorithms on GC selection that, for the first time, are applicable to ACGs and achieve the maximal memory cut-offs.

Toward Multidiversified Ensemble Clustering of High-Dimensional Data: From Subspaces to Metrics and Beyond

1 code implementation9 Oct 2017 Dong Huang, Chang-Dong Wang, Jian-Huang Lai, Chee-Keong Kwoh

The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research.

Learning Category-Specific 3D Shape Models From Weakly Labeled 2D Images

no code implementations CVPR 2017 Dingwen Zhang, Junwei Han, Yang Yang, Dong Huang

Recently, researchers have made great processes to build category-specific 3D shape models from 2D images with manual annotations consisting of class labels, keypoints, and ground truth figure-ground segmentations.

3D Shape Reconstruction Semantic Segmentation +1

Soft-Margin Mixture of Regressions

no code implementations CVPR 2017 Dong Huang, Longfei Han, Fernando de la Torre

However, existing divide-and-conquer approaches fail to deal with discontinuities between partitions (e. g., Gaussian mixture of regressions) and they cannot guarantee that the partitioned input space will be homogeneously modeled by local regressors (e. g., ordinal regression).

Age Estimation Crowd Counting +3

Ensemble-driven support vector clustering: From ensemble learning to automatic parameter estimation

no code implementations3 Aug 2016 Dong Huang, Chang-Dong Wang, Jian-Huang Lai, Yun Liang, Shan Bian, Yu Chen

Support vector clustering (SVC) is a versatile clustering technique that is able to identify clusters of arbitrary shapes by exploiting the kernel trick.

Ensemble Learning

Robust Ensemble Clustering Using Probability Trajectories

no code implementations3 Jun 2016 Dong Huang, Jian-Huang Lai, Chang-Dong Wang

To address these two limitations, in this paper, we propose a novel ensemble clustering approach based on sparse graph representation and probability trajectory analysis.

Locally Weighted Ensemble Clustering

no code implementations17 May 2016 Dong Huang, Chang-Dong Wang, Jian-Huang Lai

Although some efforts have been made to (globally) evaluate and weight the base clusterings, yet these methods tend to view each base clustering as an individual and neglect the local diversity of clusters inside the same base clustering.


Complex Non-Rigid Motion 3D Reconstruction by Union of Subspaces

no code implementations CVPR 2014 Yingying Zhu, Dong Huang, Fernando de la Torre, Simon Lucey

The task of estimating complex non-rigid 3D motion through a monocular camera is of increasing interest to the wider scientific community.

3D Reconstruction

Combining Multiple Clusterings via Crowd Agreement Estimation and Multi-Granularity Link Analysis

no code implementations6 May 2014 Dong Huang, Jian-Huang Lai, Chang-Dong Wang

We present the normalized crowd agreement index (NCAI) to evaluate the quality of base clusterings in an unsupervised manner and thus weight the base clusterings in accordance with their clustering validity.

Clustering Ensemble graph partitioning

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