Search Results for author: Thomas S. Huang

Found 69 papers, 28 papers with code

Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection

1 code implementation29 Apr 2021 Jiachen Li, Bowen Cheng, Rogerio Feris, JinJun Xiong, Thomas S. Huang, Wen-mei Hwu, Humphrey Shi

Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment methods based on the Intersection-over-Union~(IoU) metric.

Object Detection

Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation

no code implementations28 Jun 2020 Hanchao Yu, Xiao Chen, Humphrey Shi, Terrence Chen, Thomas S. Huang, Shanhui Sun

In this paper, we propose Motion Pyramid Networks, a novel deep learning-based approach for accurate and efficient cardiac motion estimation.

Knowledge Distillation Motion Estimation

Neural Sparse Representation for Image Restoration

1 code implementation NeurIPS 2020 Yuchen Fan, Jiahui Yu, Yiqun Mei, Yulun Zhang, Yun Fu, Ding Liu, Thomas S. Huang

Inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks.

Image Compression Image Denoising +2

Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining

3 code implementations CVPR 2020 Yiqun Mei, Yuchen Fan, Yuqian Zhou, Lichao Huang, Thomas S. Huang, Humphrey Shi

By combining the new CS-NL prior with local and in-scale non-local priors in a powerful recurrent fusion cell, we can find more cross-scale feature correlations within a single low-resolution (LR) image.

Image Super-Resolution

Pyramid Attention Networks for Image Restoration

2 code implementations28 Apr 2020 Yiqun Mei, Yuchen Fan, Yulun Zhang, Jiahui Yu, Yuqian Zhou, Ding Liu, Yun Fu, Thomas S. Huang, Humphrey Shi

Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales.

Demosaicking Image Denoising +1

Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation

no code implementations2 Apr 2020 Zhonghao Wang, Yunchao Wei, Rogerior Feris, JinJun Xiong, Wen-mei Hwu, Thomas S. Huang, Humphrey Shi

A key challenge of this task is how to alleviate the data distribution discrepancy between the source and target domains, i. e. reducing domain shift.

Domain Adaptation Semantic Segmentation

Laplacian Denoising Autoencoder

no code implementations30 Mar 2020 Jianbo Jiao, Linchao Bao, Yunchao Wei, Shengfeng He, Honghui Shi, Rynson Lau, Thomas S. Huang

This can be naturally generalized to span multiple scales with a Laplacian pyramid representation of the input data.

Denoising Self-Supervised Learning

Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation

1 code implementation CVPR 2020 Zhonghao Wang, Mo Yu, Yunchao Wei, Rogerio Feris, JinJun Xiong, Wen-mei Hwu, Thomas S. Huang, Humphrey Shi

We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work.

Semantic Segmentation Unsupervised Domain Adaptation

Deep Affinity Net: Instance Segmentation via Affinity

no code implementations15 Mar 2020 Xingqian Xu, Mang Tik Chiu, Thomas S. Huang, Honghui Shi

Most of the modern instance segmentation approaches fall into two categories: region-based approaches in which object bounding boxes are detected first and later used in cropping and segmenting instances; and keypoint-based approaches in which individual instances are represented by a set of keypoints followed by a dense pixel clustering around those keypoints.

graph partitioning Instance Segmentation +1

AlignSeg: Feature-Aligned Segmentation Networks

1 code implementation24 Feb 2020 Zilong Huang, Yunchao Wei, Xinggang Wang, Wenyu Liu, Thomas S. Huang, Humphrey Shi

Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic segmentation.

Semantic Segmentation

Scale-wise Convolution for Image Restoration

1 code implementation19 Dec 2019 Yuchen Fan, Jiahui Yu, Ding Liu, Thomas S. Huang

In this paper, we show that properly modeling scale-invariance into neural networks can bring significant benefits to image restoration performance.

Data Augmentation Image Compression +3

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

6 code implementations CVPR 2020 Bowen Cheng, Maxwell D. Collins, Yukun Zhu, Ting Liu, Thomas S. Huang, Hartwig Adam, Liang-Chieh Chen

In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed.

Ranked #3 on Instance Segmentation on Cityscapes test (using extra training data)

Instance Segmentation Panoptic Segmentation

Any-Precision Deep Neural Networks

2 code implementations17 Nov 2019 Haichao Yu, Haoxiang Li, Honghui Shi, Thomas S. Huang, Gang Hua

When all layers are set to low-bits, we show that the model achieved accuracy comparable to dedicated models trained at the same precision.


2 code implementations10 Oct 2019 Bowen Cheng, Maxwell D. Collins, Yukun Zhu, Ting Liu, Thomas S. Huang, Hartwig Adam, Liang-Chieh Chen

The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e. g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression.

Instance Segmentation Panoptic Segmentation

Towards Learning a Self-inverse Network for Bidirectional Image-to-image Translation

no code implementations9 Sep 2019 Zengming Shen, Yifan Chen, S. Kevin Zhou, Bogdan Georgescu, Xuqi Liu, Thomas S. Huang

A self-inverse network shares several distinct advantages: only one network instead of two, better generalization and more restricted parameter space.

Image-to-Image Translation Translation

FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary

no code implementations ICLR 2020 Yingzhen Yang, Jiahui Yu, Nebojsa Jojic, Jun Huan, Thomas S. Huang

FSNet has the same architecture as that of the baseline CNN to be compressed, and each convolution layer of FSNet has the same number of filters from FS as that of the basline CNN in the forward process.

General Classification Image Classification +3

An Empirical Study on Regularization of Deep Neural Networks by Local Rademacher Complexity

no code implementations3 Feb 2019 Yingzhen Yang, Jiahui Yu, Xingjian Li, Jun Huan, Thomas S. Huang

In this paper, we investigate the role of Rademacher complexity in improving generalization of DNNs and propose a novel regularizer rooted in Local Rademacher Complexity (LRC).

Neural Architecture Search

CCNet: Criss-Cross Attention for Semantic Segmentation

2 code implementations ICCV 2019 Zilong Huang, Xinggang Wang, Yunchao Wei, Lichao Huang, Humphrey Shi, Wenyu Liu, Thomas S. Huang

Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage.

Ranked #6 on Semantic Segmentation on FoodSeg103 (using extra training data)

Human Parsing Instance Segmentation +5

A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization

no code implementations23 Nov 2018 Bowen Cheng, Yunchao Wei, Jiahui Yu, Shiyu Chang, JinJun Xiong, Wen-mei Hwu, Thomas S. Huang, Humphrey Shi

While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in an easy-to-hard manner and on the selected examples progressively.

General Classification Image Classification +5

Connecting Image Denoising and High-Level Vision Tasks via Deep Learning

1 code implementation6 Sep 2018 Ding Liu, Bihan Wen, Jianbo Jiao, Xian-Ming Liu, Zhangyang Wang, Thomas S. Huang

Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation.

Image Denoising

Non-Local Recurrent Network for Image Restoration

1 code implementation NeurIPS 2018 Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, Thomas S. Huang

The main contributions of this work are: (1) Unlike existing methods that measure self-similarity in an isolated manner, the proposed non-local module can be flexibly integrated into existing deep networks for end-to-end training to capture deep feature correlation between each location and its neighborhood.

Image Denoising Image Restoration +1

Generative Image Inpainting with Contextual Attention

28 code implementations CVPR 2018 Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, Thomas S. Huang

Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.

Image Inpainting

Enhance Visual Recognition under Adverse Conditions via Deep Networks

no code implementations20 Dec 2017 Ding Liu, Bowen Cheng, Zhangyang Wang, Haichao Zhang, Thomas S. Huang

Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage.

Data Augmentation Image Restoration +3

Dilated Recurrent Neural Networks

2 code implementations NeurIPS 2017 Shiyu Chang, Yang Zhang, Wei Han, Mo Yu, Xiaoxiao Guo, Wei Tan, Xiaodong Cui, Michael Witbrock, Mark Hasegawa-Johnson, Thomas S. Huang

To provide a theory-based quantification of the architecture's advantages, we introduce a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing measures.

Sequential Image Classification

Robust Emotion Recognition from Low Quality and Low Bit Rate Video: A Deep Learning Approach

no code implementations10 Sep 2017 Bowen Cheng, Zhangyang Wang, Zhaobin Zhang, Zhu Li, Ding Liu, Jianchao Yang, Shuai Huang, Thomas S. Huang

Emotion recognition from facial expressions is tremendously useful, especially when coupled with smart devices and wireless multimedia applications.

Emotion Recognition Super-Resolution

On the Suboptimality of Proximal Gradient Descent for $\ell^{0}$ Sparse Approximation

no code implementations5 Sep 2017 Yingzhen Yang, Jiashi Feng, Nebojsa Jojic, Jianchao Yang, Thomas S. Huang

We study the proximal gradient descent (PGD) method for $\ell^{0}$ sparse approximation problem as well as its accelerated optimization with randomized algorithms in this paper.

Compressive Sensing Dimensionality Reduction

Discriminative Similarity for Clustering and Semi-Supervised Learning

no code implementations5 Sep 2017 Yingzhen Yang, Feng Liang, Nebojsa Jojic, Shuicheng Yan, Jiashi Feng, Thomas S. Huang

By generalization analysis via Rademacher complexity, the generalization error bound for the kernel classifier learned from hypothetical labeling is expressed as the sum of pairwise similarity between the data from different classes, parameterized by the weights of the kernel classifier.

When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach

2 code implementations14 Jun 2017 Ding Liu, Bihan Wen, Xianming Liu, Zhangyang Wang, Thomas S. Huang

Conventionally, image denoising and high-level vision tasks are handled separately in computer vision.

Image Denoising

Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation

no code implementations8 Dec 2016 Xianming Liu, Amy Zhang, Tobias Tiecke, Andreas Gros, Thomas S. Huang

Learning from weakly-supervised data is one of the main challenges in machine learning and computer vision, especially for tasks such as image semantic segmentation where labeling is extremely expensive and subjective.

Semantic Segmentation

Fast Wavenet Generation Algorithm

6 code implementations29 Nov 2016 Tom Le Paine, Pooya Khorrami, Shiyu Chang, Yang Zhang, Prajit Ramachandran, Mark A. Hasegawa-Johnson, Thomas S. Huang

This paper presents an efficient implementation of the Wavenet generation process called Fast Wavenet.

Deep Double Sparsity Encoder: Learning to Sparsify Not Only Features But Also Parameters

no code implementations23 Aug 2016 Zhangyang Wang, Thomas S. Huang

This paper emphasizes the significance to jointly exploit the problem structure and the parameter structure, in the context of deep modeling.

Dictionary Learning

Stacked Approximated Regression Machine: A Simple Deep Learning Approach

no code implementations14 Aug 2016 Zhangyang Wang, Shiyu Chang, Qing Ling, Shuai Huang, Xia Hu, Honghui Shi, Thomas S. Huang

With the agreement of my coauthors, I Zhangyang Wang would like to withdraw the manuscript "Stacked Approximated Regression Machine: A Simple Deep Learning Approach".

Streaming Recommender Systems

no code implementations21 Jul 2016 Shiyu Chang, Yang Zhang, Jiliang Tang, Dawei Yin, Yi Chang, Mark A. Hasegawa-Johnson, Thomas S. Huang

The increasing popularity of real-world recommender systems produces data continuously and rapidly, and it becomes more realistic to study recommender systems under streaming scenarios.

Recommendation Systems

D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images

no code implementations CVPR 2016 Zhangyang Wang, Ding Liu, Shiyu Chang, Qing Ling, Yingzhen Yang, Thomas S. Huang

In this paper, we design a Deep Dual-Domain (D3) based fast restoration model to remove artifacts of JPEG compressed images.

Learning A Deep $\ell_\infty$ Encoder for Hashing

no code implementations6 Apr 2016 Zhangyang Wang, Yingzhen Yang, Shiyu Chang, Qing Ling, Thomas S. Huang

We investigate the $\ell_\infty$-constrained representation which demonstrates robustness to quantization errors, utilizing the tool of deep learning.


Seq-NMS for Video Object Detection

1 code implementation26 Feb 2016 Wei Han, Pooya Khorrami, Tom Le Paine, Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, Thomas S. Huang

Video object detection is challenging because objects that are easily detected in one frame may be difficult to detect in another frame within the same clip.

Frame General Classification +3

How Deep Neural Networks Can Improve Emotion Recognition on Video Data

1 code implementation24 Feb 2016 Pooya Khorrami, Tom Le Paine, Kevin Brady, Charlie Dagli, Thomas S. Huang

In this work, we present a system that performs emotion recognition on video data using both CNNs and RNNs, and we also analyze how much each neural network component contributes to the system's overall performance.

Emotion Recognition

$\mathbf{D^3}$: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images

no code implementations16 Jan 2016 Zhangyang Wang, Ding Liu, Shiyu Chang, Qing Ling, Yingzhen Yang, Thomas S. Huang

In this paper, we design a Deep Dual-Domain ($\mathbf{D^3}$) based fast restoration model to remove artifacts of JPEG compressed images.

Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks

no code implementations ICCV 2015 Chunshui Cao, Xian-Ming Liu, Yi Yang, Yinan Yu, Jiang Wang, Zilei Wang, Yongzhen Huang, Liang Wang, Chang Huang, Wei Xu, Deva Ramanan, Thomas S. Huang

While feedforward deep convolutional neural networks (CNNs) have been a great success in computer vision, it is important to remember that the human visual contex contains generally more feedback connections than foward connections.

Learning with $\ell^{0}$-Graph: $\ell^{0}$-Induced Sparse Subspace Clustering

no code implementations28 Oct 2015 Yingzhen Yang, Jiashi Feng, Jianchao Yang, Thomas S. Huang

Sparse subspace clustering methods, such as Sparse Subspace Clustering (SSC) \cite{ElhamifarV13} and $\ell^{1}$-graph \cite{YanW09, ChengYYFH10}, are effective in partitioning the data that lie in a union of subspaces.

Do Deep Neural Networks Learn Facial Action Units When Doing Expression Recognition?

1 code implementation10 Oct 2015 Pooya Khorrami, Tom Le Paine, Thomas S. Huang

Despite being the appearance-based classifier of choice in recent years, relatively few works have examined how much convolutional neural networks (CNNs) can improve performance on accepted expression recognition benchmarks and, more importantly, examine what it is they actually learn.

Learning Deep $\ell_0$ Encoders

no code implementations1 Sep 2015 Zhangyang Wang, Qing Ling, Thomas S. Huang

We study the $\ell_0$ sparse approximation problem with the tool of deep learning, by proposing Deep $\ell_0$ Encoders.

Learning A Task-Specific Deep Architecture For Clustering

no code implementations1 Sep 2015 Zhangyang Wang, Shiyu Chang, Jiayu Zhou, Meng Wang, Thomas S. Huang

In this paper, we propose to emulate the sparse coding-based clustering pipeline in the context of deep learning, leading to a carefully crafted deep model benefiting from both.

DeepFont: Identify Your Font from An Image

1 code implementation12 Jul 2015 Zhangyang Wang, Jianchao Yang, Hailin Jin, Eli Shechtman, Aseem Agarwala, Jonathan Brandt, Thomas S. Huang

As font is one of the core design concepts, automatic font identification and similar font suggestion from an image or photo has been on the wish list of many designers.

Domain Adaptation Font Recognition +1

Understanding Image Structure via Hierarchical Shape Parsing

no code implementations CVPR 2015 Xian-Ming Liu, Rongrong Ji, Changhu Wang, Wei Liu, Bineng Zhong, Thomas S. Huang

A hierarchical shape parsing strategy is proposed to partition and organize image components into a hierarchical structure in the scale space.

Designing A Composite Dictionary Adaptively From Joint Examples

no code implementations12 Mar 2015 Zhangyang Wang, Yingzhen Yang, Jianchao Yang, Thomas S. Huang

We study the complementary behaviors of external and internal examples in image restoration, and are motivated to formulate a composite dictionary design framework.

Image Denoising Image Restoration +1

Learning Super-Resolution Jointly from External and Internal Examples

no code implementations3 Mar 2015 Zhangyang Wang, Yingzhen Yang, Zhaowen Wang, Shiyu Chang, Jianchao Yang, Thomas S. Huang

Single image super-resolution (SR) aims to estimate a high-resolution (HR) image from a lowresolution (LR) input.

Image Super-Resolution

An Analysis of Unsupervised Pre-training in Light of Recent Advances

2 code implementations20 Dec 2014 Tom Le Paine, Pooya Khorrami, Wei Han, Thomas S. Huang

We discover unsupervised pre-training, as expected, helps when the ratio of unsupervised to supervised samples is high, and surprisingly, hurts when the ratio is low.

Data Augmentation Image Classification +2

On a Theory of Nonparametric Pairwise Similarity for Clustering: Connecting Clustering to Classification

no code implementations NeurIPS 2014 Yingzhen Yang, Feng Liang, Shuicheng Yan, Zhangyang Wang, Thomas S. Huang

Modeling the underlying data distribution by nonparametric kernel density estimation, the generalization error bounds for both unsupervised nonparametric classifiers are the sum of nonparametric pairwise similarity terms between the data points for the purpose of clustering.

Density Estimation General Classification +1

Learning Locally-Adaptive Decision Functions for Person Verification

no code implementations CVPR 2013 Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith

This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule.

Face Verification Metric Learning +1

Nonparametric Unsupervised Classification

no code implementations2 Oct 2012 Yingzhen Yang, Thomas S. Huang

Unsupervised classification methods learn a discriminative classifier from unlabeled data, which has been proven to be an effective way of simultaneously clustering the data and training a classifier from the data.

Classification General Classification

Learning to Search Efficiently in High Dimensions

no code implementations NeurIPS 2011 Zhen Li, Huazhong Ning, Liangliang Cao, Tong Zhang, Yihong Gong, Thomas S. Huang

Traditional approaches relied on algorithmic constructions that are often data independent (such as Locality Sensitive Hashing) or weakly dependent (such as kd-trees, k-means trees).

Graph Regularized Nonnegative Matrix Factorization for Data Representation

no code implementations IEEE Transactions on Pattern Analysis and Machine Intelligence 2011 Deng Cai, Xiaofei He, Jiawei Han, Thomas S. Huang

In GNMF, an affinity graph is constructed to encode the geometrical information and we seek a matrix factorization, which respects the graph structure.

Information Retrieval

Bregman Distance to L1 Regularized Logistic Regression

no code implementations21 Apr 2010 Mithun Das Gupta, Thomas S. Huang

In this work we investigate the relationship between Bregman distances and regularized Logistic Regression model.

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