Search Results for author: Shiqi Wang

Found 95 papers, 46 papers with code

Perceptual Quality Assessment of 360$^\circ$ Images Based on Generative Scanpath Representation

1 code implementation7 Sep 2023 Xiangjie Sui, Hanwei Zhu, Xuelin Liu, Yuming Fang, Shiqi Wang, Zhou Wang

To address these issues, we introduce a unique generative scanpath representation (GSR) for effective quality inference of 360$^\circ$ images, which aggregates varied perceptual experiences of multi-hypothesis users under a predefined viewing condition.

Image Quality Assessment

Extreme Image Compression using Fine-tuned VQGAN Models

no code implementations17 Jul 2023 Qi Mao, Tinghan Yang, Yinuo Zhang, Shuyin Pan, Meng Wang, Shiqi Wang, Siwei Ma

Recent advances in generative compression methods have demonstrated remarkable progress in enhancing the perceptual quality of compressed data, especially in scenarios with low bitrates.

Image Compression Quantization

Glow in the Dark: Low-Light Image Enhancement with External Memory

1 code implementation IEEE Transactions on Multimedia 2023 Dongjie Ye, Zhangkai Ni, Wenhan Yang, Hanli Wang, Shiqi Wang, Sam Kwong

Benefiting from the learned memory, more complex distributions of reference images in the entire dataset can be “remembered” to facilitate the adjustment of the testing samples more adaptively.

Low-Light Image Enhancement

Shifting Attention to Relevance: Towards the Uncertainty Estimation of Large Language Models

1 code implementation3 Jul 2023 Jinhao Duan, Hao Cheng, Shiqi Wang, Chenan Wang, Alex Zavalny, Renjing Xu, Bhavya Kailkhura, Kaidi Xu

Our research is derived from the heuristic facts that tokens are created unequally in reflecting the meaning of generations by auto-regressive LLMs, i. e., some tokens are more relevant (or representative) than others, yet all the tokens are equally valued when estimating uncertainty.

Question Answering Text Generation

The Age of Synthetic Realities: Challenges and Opportunities

no code implementations9 Jun 2023 João Phillipe Cardenuto, Jing Yang, Rafael Padilha, Renjie Wan, Daniel Moreira, Haoliang Li, Shiqi Wang, Fernanda Andaló, Sébastien Marcel, Anderson Rocha

Synthetic realities are digital creations or augmentations that are contextually generated through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of data to construct new narratives or realities, regardless of the intent to deceive.


Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization

1 code implementation5 Jun 2023 Yibing Liu, Chris Xing Tian, Haoliang Li, Lei Ma, Shiqi Wang

Leveraging our NAC, we show that 1) InD and OOD inputs can be naturally separated based on the neuron behavior, which significantly eases the OOD detection problem and achieves a record-breaking performance of 0. 03% FPR95 on ResNet-50, outperforming the previous best method by 20. 67%; 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness.

Out-of-Distribution Detection

Geometric Prior Based Deep Human Point Cloud Geometry Compression

no code implementations2 May 2023 Xinju Wu, Pingping Zhang, Meng Wang, Peilin Chen, Shiqi Wang, Sam Kwong

The emergence of digital avatars has raised an exponential increase in the demand for human point clouds with realistic and intricate details.

Optimization-Inspired Cross-Attention Transformer for Compressive Sensing

1 code implementation CVPR 2023 Jiechong Song, Chong Mou, Shiqi Wang, Siwei Ma, Jian Zhang

And, PGCA block achieves an enhanced information interaction, which introduces the inertia force into the gradient descent step through a cross attention block.

Compressive Sensing

Perceptual Quality Assessment of Face Video Compression: A Benchmark and An Effective Method

1 code implementation14 Apr 2023 Yixuan Li, Bolin Chen, Baoliang Chen, Meng Wang, Shiqi Wang

In this paper, we introduce the large-scale Compressed Face Video Quality Assessment (CFVQA) database, which is the first attempt to systematically understand the perceptual quality and diversified compression distortions in face videos.

Video Compression Video Quality Assessment +1

Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptation

no code implementations2 Mar 2023 Chenqi Kong, Haoliang Li, Shiqi Wang

Nowadays, forgery faces pose pressing security concerns over fake news, fraud, impersonation, etc.

Face Detection

Debiased Mapping for Full-Reference Image Quality Assessment

no code implementations22 Feb 2023 Baoliang Chen, Hanwei Zhu, Lingyu Zhu, Shiqi Wang

To account for this, we develop the Debiased Mapping based quality Measure (DMM), which relies on the orthonormal bases of deep learning features formed by singular value decomposition (SVD).

Image Quality Assessment

Interactive Face Video Coding: A Generative Compression Framework

1 code implementation20 Feb 2023 Bolin Chen, Zhao Wang, Binzhe Li, Shurun Wang, Shiqi Wang, Yan Ye

In this paper, we propose a novel framework for Interactive Face Video Coding (IFVC), which allows humans to interact with the intrinsic visual representations instead of the signals.

Are Diffusion Models Vulnerable to Membership Inference Attacks?

1 code implementation2 Feb 2023 Jinhao Duan, Fei Kong, Shiqi Wang, Xiaoshuang Shi, Kaidi Xu

In this paper, we investigate the vulnerability of diffusion models to Membership Inference Attacks (MIAs), a common privacy concern.

Image Generation

M3FAS: An Accurate and Robust MultiModal Mobile Face Anti-Spoofing System

no code implementations30 Jan 2023 Chenqi Kong, Kexin Zheng, Yibing Liu, Shiqi Wang, Anderson Rocha, Haoliang Li

The innovation of this work mainly lies in the following aspects: (1) To achieve robust PAD, our system combines visual and auditory modalities using three pervasively available sensors: camera, speaker, and microphone; (2) We design a novel two-branch neural network with three hierarchical feature aggregation modules to perform cross-modal feature fusion; (3).

Face Anti-Spoofing Face Recognition

ReCode: Robustness Evaluation of Code Generation Models

2 code implementations20 Dec 2022 Shiqi Wang, Zheng Li, Haifeng Qian, Chenghao Yang, Zijian Wang, Mingyue Shang, Varun Kumar, Samson Tan, Baishakhi Ray, Parminder Bhatia, Ramesh Nallapati, Murali Krishna Ramanathan, Dan Roth, Bing Xiang

Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation.

Code Generation

Two-branch Multi-scale Deep Neural Network for Generalized Document Recapture Attack Detection

1 code implementation30 Nov 2022 Jiaxing Li, Chenqi Kong, Shiqi Wang, Haoliang Li

The image recapture attack is an effective image manipulation method to erase certain forensic traces, and when targeting on personal document images, it poses a great threat to the security of e-commerce and other web applications.

Image Manipulation

Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning

no code implementations13 Nov 2022 Yibing Liu, Chris Xing Tian, Haoliang Li, Shiqi Wang

Learning invariant representations via contrastive learning has seen state-of-the-art performance in domain generalization (DG).

Contrastive Learning Domain Generalization

From Distance to Dependency: A Paradigm Shift of Full-reference Image Quality Assessment

no code implementations9 Nov 2022 Hanwei Zhu, Baoliang Chen, Lingyu Zhu, Shiqi Wang

Deep learning-based full-reference image quality assessment (FR-IQA) models typically rely on the feature distance between the reference and distorted images.

Image Quality Assessment

Multi-lingual Evaluation of Code Generation Models

1 code implementation26 Oct 2022 Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang, Xiaopeng Li, Yuchen Tian, Ming Tan, Wasi Uddin Ahmad, Shiqi Wang, Qing Sun, Mingyue Shang, Sujan Kumar Gonugondla, Hantian Ding, Varun Kumar, Nathan Fulton, Arash Farahani, Siddhartha Jain, Robert Giaquinto, Haifeng Qian, Murali Krishna Ramanathan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta, Dan Roth, Bing Xiang

Using these benchmarks, we are able to assess the performance of code generation models in a multi-lingual fashion, and discovered generalization ability of language models on out-of-domain languages, advantages of multi-lingual models over mono-lingual, the ability of few-shot prompting to teach the model new languages, and zero-shot translation abilities even on mono-lingual settings.

Code Completion Code Translation +1

Digital and Physical Face Attacks: Reviewing and One Step Further

no code implementations29 Sep 2022 Chenqi Kong, Shiqi Wang, Haoliang Li

With the rapid progress over the past five years, face authentication has become the most pervasive biometric recognition method.

Face Recognition

Learning from Mixed Datasets: A Monotonic Image Quality Assessment Model

1 code implementation21 Sep 2022 Zhaopeng Feng, Keyang Zhang, Shuyue Jia, Baoliang Chen, Shiqi Wang

Deep learning based image quality assessment (IQA) models usually learn to predict image quality from a single dataset, leading the model to overfit specific scenes.

Image Quality Assessment

Just Noticeable Difference Modeling for Face Recognition System

no code implementations13 Sep 2022 Yu Tian, Zhangkai Ni, Baoliang Chen, Shurun Wang, Shiqi Wang, Hanli Wang, Sam Kwong

In particular, in order to maximum redundancy removal without impairment of robust identity information, we apply the encoder with multiple feature extraction and attention-based feature decomposition modules to progressively decompose face features into two uncorrelated components, i. e., identity and residual features, via self-supervised learning.

Face Recognition Self-Supervised Learning

Deep Feature Statistics Mapping for Generalized Screen Content Image Quality Assessment

1 code implementation12 Sep 2022 Baoliang Chen, Hanwei Zhu, Lingyu Zhu, Shiqi Wang, Sam Kwong

The underlying mechanism of the proposed approach is based upon the wild assumption that the SCIs, which are not physically acquired, still obey certain statistics that could be understood in a learning fashion.

No-Reference Image Quality Assessment

A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels

2 code implementations7 Sep 2022 Runmin Cong, Qi Qin, Chen Zhang, Qiuping Jiang, Shiqi Wang, Yao Zhao, Sam Kwong

In this paper, we focus on a new weakly-supervised SOD task under hybrid labels, where the supervision labels include a large number of coarse labels generated by the traditional unsupervised method and a small number of real labels.

object-detection RGB Salient Object Detection +3

High Dynamic Range Image Quality Assessment Based on Frequency Disparity

1 code implementation6 Sep 2022 Yue Liu, Zhangkai Ni, Shiqi Wang, Hanli Wang, Sam Kwong

In this paper, a novel and effective image quality assessment (IQA) algorithm based on frequency disparity for high dynamic range (HDR) images is proposed, termed as local-global frequency feature-based model (LGFM).

Image Quality Assessment Vocal Bursts Intensity Prediction

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

2 code implementations11 Aug 2022 huan zhang, Shiqi Wang, Kaidi Xu, Linyi Li, Bo Li, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter

Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods.

DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space

1 code implementation5 Aug 2022 Xigran Liao, Baoliang Chen, Hanwei Zhu, Shiqi Wang, Mingliang Zhou, Sam Kwong

Existing deep learning-based full-reference IQA (FR-IQA) models usually predict the image quality in a deterministic way by explicitly comparing the features, gauging how severely distorted an image is by how far the corresponding feature lies from the space of the reference images.

Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement

no code implementations3 Jul 2022 Zhangkai Ni, Wenhan Yang, Hanli Wang, Shiqi Wang, Lin Ma, Sam Kwong

Getting rid of the fundamental limitations in fitting to the paired training data, recent unsupervised low-light enhancement methods excel in adjusting illumination and contrast of images.

Low-Light Image Enhancement

Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder

1 code implementation16 May 2022 Tiexin Qin, Shiqi Wang, Haoliang Li

Domain generalization aims to improve the generalization capability of machine learning systems to out-of-distribution (OOD) data.

Evolving Domain Generalization

CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System

1 code implementation4 Apr 2022 Chongming Gao, Shiqi Wang, Shijun Li, Jiawei Chen, Xiangnan He, Wenqiang Lei, Biao Li, Yuan Zhang, Peng Jiang

The basic idea is to first learn a causal user model on historical data to capture the overexposure effect of items on user satisfaction.

Causal Inference Offline RL +1

Distortion-Aware Loop Filtering of Intra 360^o Video Coding with Equirectangular Projection

no code implementations20 Feb 2022 Pingping Zhang, Xu Wang, Linwei Zhu, Yun Zhang, Shiqi Wang, Sam Kwong

In this paper, we propose a distortion-aware loop filtering model to improve the performance of intra coding for 360$^o$ videos projected via equirectangular projection (ERP) format.

Image Reconstruction

The Loop Game: Quality Assessment and Optimization for Low-Light Image Enhancement

no code implementations20 Feb 2022 Baoliang Chen, Lingyu Zhu, Hanwei Zhu, Wenhan Yang, Fangbo Lu, Shiqi Wang

In particular, we create a large-scale database for QUality assessment Of The Enhanced LOw-Light Image (QUOTE-LOL), which serves as the foundation in studying and developing objective quality assessment measures.

Low-Light Image Enhancement

Who Are the Best Adopters? User Selection Model for Free Trial Item Promotion

no code implementations19 Feb 2022 Shiqi Wang, Chongming Gao, Min Gao, Junliang Yu, Zongwei Wang, Hongzhi Yin

By providing users with opportunities to experience goods without charge, a free trial makes adopters know more about products and thus encourages their willingness to buy.

Marketing reinforcement-learning +1

Generalized Visual Quality Assessment of GAN-Generated Face Images

no code implementations28 Jan 2022 Yu Tian, Zhangkai Ni, Baoliang Chen, Shiqi Wang, Hanli Wang, Sam Kwong

However, little work has been dedicated to automatic quality assessment of such GAN-generated face images (GFIs), even less have been devoted to generalized and robust quality assessment of GFIs generated with unseen GAN model.

Face Generation Image Quality Assessment +1

CSformer: Bridging Convolution and Transformer for Compressive Sensing

no code implementations31 Dec 2021 Dongjie Ye, Zhangkai Ni, Hanli Wang, Jian Zhang, Shiqi Wang, Sam Kwong

The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery.

Compressive Sensing Inductive Bias +1

Locally Adaptive Structure and Texture Similarity for Image Quality Assessment

no code implementations16 Oct 2021 Keyan Ding, Yi Liu, Xueyi Zou, Shiqi Wang, Kede Ma

The latest advances in full-reference image quality assessment (IQA) involve unifying structure and texture similarity based on deep representations.

Image Quality Assessment Image Super-Resolution

A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks

no code implementations29 Sep 2021 huan zhang, Shiqi Wang, Kaidi Xu, Yihan Wang, Suman Jana, Cho-Jui Hsieh, J Zico Kolter

In this work, we formulate an adversarial attack using a branch-and-bound (BaB) procedure on ReLU neural networks and search adversarial examples in the activation space corresponding to binary variables in a mixed integer programming (MIP) formulation.

Adversarial Attack

Towards Top-Down Just Noticeable Difference Estimation of Natural Images

1 code implementation11 Aug 2021 Qiuping Jiang, Zhentao Liu, Shiqi Wang, Feng Shao, Weisi Lin

Instead of explicitly formulating and fusing different masking effects in a bottom-up way, the proposed JND estimation model dedicates to first predicting a critical perceptual lossless (CPL) counterpart of the original image and then calculating the difference map between the original image and the predicted CPL image as the JND map.

Image Compression Image Reconstruction +1

No-Reference Image Quality Assessment by Hallucinating Pristine Features

1 code implementation9 Aug 2021 Baoliang Chen, Lingyu Zhu, Chenqi Kong, Hanwei Zhu, Shiqi Wang, Zhu Li

In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination.

Disentanglement No-Reference Image Quality Assessment

Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-level Telltales

1 code implementation13 Jul 2021 Chenqi Kong, Baoliang Chen, Haoliang Li, Shiqi Wang, Anderson Rocha, Sam Kwong

The technological advancements of deep learning have enabled sophisticated face manipulation schemes, raising severe trust issues and security concerns in modern society.

Decision Making

End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization

no code implementations1 Jul 2021 Shurun Wang, Zhao Wang, Shiqi Wang, Yan Ye

In this paper, we show that the design and optimization of network architecture could be further improved for compression towards machine vision.

object-detection Object Detection

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification

no code implementations NeurIPS 2021 Shiqi Wang, huan zhang, Kaidi Xu, Xue Lin, Suman Jana, Cho-Jui Hsieh, J Zico Kolter

We develop $\beta$-CROWN, a new bound propagation based method that can fully encode neuron split constraints in branch-and-bound (BaB) based complete verification via optimizable parameters $\beta$.

Learning Security Classifiers with Verified Global Robustness Properties

1 code implementation24 May 2021 Yizheng Chen, Shiqi Wang, Yue Qin, Xiaojing Liao, Suman Jana, David Wagner

Since data distribution shift is very common in security applications, e. g., often observed for malware detection, local robustness cannot guarantee that the property holds for unseen inputs at the time of deploying the classifier.

Malware Detection

Privacy-Preserving Constrained Domain Generalization via Gradient Alignment

no code implementations14 May 2021 Chris Xing Tian, Haoliang Li, YuFei Wang, Shiqi Wang

However, due to the issue of limited dataset availability and the strict legal and ethical requirements for patient privacy protection, the broad applications of medical imaging classification driven by DNN with large-scale training data have been largely hindered.

Domain Generalization Federated Learning +3

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification

4 code implementations NeurIPS 2021 Shiqi Wang, huan zhang, Kaidi Xu, Xue Lin, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter

Compared to the typically tightest but very costly semidefinite programming (SDP) based incomplete verifiers, we obtain higher verified accuracy with three orders of magnitudes less verification time.

Adversarial Attack

Neuron Coverage-Guided Domain Generalization

no code implementations27 Feb 2021 Chris Xing Tian, Haoliang Li, Xiaofei Xie, Yang Liu, Shiqi Wang

More specifically, by treating the DNN as a program and each neuron as a functional point of the code, during the network training we aim to improve the generalization capability by maximizing the neuron coverage of DNN with the gradient similarity regularization between the original and augmented samples.

DNN Testing Domain Generalization

Camera Invariant Feature Learning for Generalized Face Anti-spoofing

no code implementations25 Jan 2021 Baoliang Chen, Wenhan Yang, Haoliang Li, Shiqi Wang, Sam Kwong

The first branch aims to learn the camera invariant spoofing features via feature level decomposition in the high frequency domain.

Face Anti-Spoofing

Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network

1 code implementation30 Dec 2020 Zhangkai Ni, Wenhan Yang, Shiqi Wang, Lin Ma, Sam Kwong

In this paper, we present an unsupervised image enhancement generative adversarial network (UEGAN), which learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner, rather than learning on a large number of paired images.

Image Enhancement L2 Regularization

Unpaired Image Enhancement with Quality-Attention Generative Adversarial Network

no code implementations30 Dec 2020 Zhangkai Ni, Wenhan Yang, Shiqi Wang, Lin Ma, Sam Kwong

The key novelty of the proposed QAGAN lies in the injected QAM for the generator such that it learns domain-relevant quality attention directly from the two domains.

Image Enhancement

Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessment

1 code implementation27 Dec 2020 Baoliang Chen, Lingyu Zhu, Guo Li, Hongfei Fan, Shiqi Wang

In this work, we propose a no-reference video quality assessment method, aiming to achieve high-generalization capability in cross-content, -resolution and -frame rate quality prediction.

Video Quality Assessment

Adaptive Verifiable Training Using Pairwise Class Similarity

no code implementations14 Dec 2020 Shiqi Wang, Kevin Eykholt, Taesung Lee, Jiyong Jang, Ian Molloy

On CIFAR10, a non-robust LeNet model has a 21. 63% error rate, while a model created using verifiable training and a L-infinity robustness criterion of 8/255, has an error rate of 57. 10%.

Conceptual Compression via Deep Structure and Texture Synthesis

2 code implementations10 Nov 2020 Jianhui Chang, Zhenghui Zhao, Chuanmin Jia, Shiqi Wang, Lingbo Yang, Qi Mao, Jian Zhang, Siwei Ma

To this end, we propose a novel conceptual compression framework that encodes visual data into compact structure and texture representations, then decodes in a deep synthesis fashion, aiming to achieve better visual reconstruction quality, flexible content manipulation, and potential support for various vision tasks.

Texture Synthesis

DRL-FAS: A Novel Framework Based on Deep Reinforcement Learning for Face Anti-Spoofing

no code implementations16 Sep 2020 Rizhao Cai, Haoliang Li, Shiqi Wang, Changsheng chen, Alex ChiChung Kot

Inspired by the philosophy employed by human beings to determine whether a presented face example is genuine or not, i. e., to glance at the example globally first and then carefully observe the local regions to gain more discriminative information, for the face anti-spoofing problem, we propose a novel framework based on the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN).

Face Anti-Spoofing Philosophy +1

Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems

no code implementations15 Sep 2020 Haoliang Li, Yufei Wang, Xiaofei Xie, Yang Liu, Shiqi Wang, Renjie Wan, Lap-Pui Chau, Alex C. Kot

In this paper, we propose a novel black-box backdoor attack technique on face recognition systems, which can be conducted without the knowledge of the targeted DNN model.

Backdoor Attack Face Recognition

No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptation

no code implementations19 Aug 2020 Baoliang Chen, Haoliang Li, Hongfei Fan, Shiqi Wang

Here, we develop the first unsupervised domain adaptation based no reference quality assessment method for SCIs, leveraging rich subjective ratings of the natural images (NIs).

Image Quality Assessment Learning-To-Rank +2

Towards Modality Transferable Visual Information Representation with Optimal Model Compression

no code implementations13 Aug 2020 Rongqun Lin, Linwei Zhu, Shiqi Wang, Sam Kwong

Compactly representing the visual signals is of fundamental importance in various image/video-centered applications.

Model Compression Philosophy

Towards Understanding Fast Adversarial Training

no code implementations4 Jun 2020 Bai Li, Shiqi Wang, Suman Jana, Lawrence Carin

Current neural-network-based classifiers are susceptible to adversarial examples.

Iterative Network for Image Super-Resolution

1 code implementation20 May 2020 Yuqing Liu, Shiqi Wang, Jian Zhang, Shanshe Wang, Siwei Ma, Wen Gao

A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization.

Image Super-Resolution SSIM

Comparison of Image Quality Models for Optimization of Image Processing Systems

1 code implementation4 May 2020 Keyan Ding, Kede Ma, Shiqi Wang, Eero P. Simoncelli

The performance of objective image quality assessment (IQA) models has been evaluated primarily by comparing model predictions to human quality judgments.

Deblurring Denoising +2

Towards Analysis-friendly Face Representation with Scalable Feature and Texture Compression

no code implementations21 Apr 2020 Shurun Wang, Shiqi Wang, Wenhan Yang, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Wen Gao

In particular, we study the feature and texture compression in a scalable coding framework, where the base layer serves as the deep learning feature and enhancement layer targets to perfectly reconstruct the texture.

Image Compression

Image Quality Assessment: Unifying Structure and Texture Similarity

2 code implementations16 Apr 2020 Keyan Ding, Kede Ma, Shiqi Wang, Eero P. Simoncelli

Objective measures of image quality generally operate by comparing pixels of a "degraded" image to those of the original.

Image Quality Assessment Retrieval +1

Towards Practical Lottery Ticket Hypothesis for Adversarial Training

1 code implementation6 Mar 2020 Bai Li, Shiqi Wang, Yunhan Jia, Yantao Lu, Zhenyu Zhong, Lawrence Carin, Suman Jana

Recent research has proposed the lottery ticket hypothesis, suggesting that for a deep neural network, there exist trainable sub-networks performing equally or better than the original model with commensurate training steps.

HYDRA: Pruning Adversarially Robust Neural Networks

3 code implementations NeurIPS 2020 Vikash Sehwag, Shiqi Wang, Prateek Mittal, Suman Jana

We demonstrate that our approach, titled HYDRA, achieves compressed networks with state-of-the-art benign and robust accuracy, simultaneously.

Network Pruning

ARMA Nets: Expanding Receptive Field for Dense Prediction

1 code implementation NeurIPS 2020 Jiahao Su, Shiqi Wang, Furong Huang

In this work, we propose to replace any traditional convolutional layer with an autoregressive moving-average (ARMA) layer, a novel module with an adjustable receptive field controlled by the learnable autoregressive coefficients.

Image Classification Semantic Segmentation +1

End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement

no code implementations10 Feb 2020 Shurun Wang, Wenhan Yang, Shiqi Wang

In this paper, we propose a novel end-to-end feature compression scheme by leveraging the representation and learning capability of deep neural networks, towards intelligent front-end equipped analysis with promising accuracy and efficiency.

Feature Compression

Single Image Deraining: From Model-Based to Data-Driven and Beyond

no code implementations16 Dec 2019 Wenhan Yang, Robby T. Tan, Shiqi Wang, Yuming Fang, Jiaying Liu

The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation.

Single Image Deraining

Cost-Aware Robust Tree Ensembles for Security Applications

2 code implementations3 Dec 2019 Yizheng Chen, Shiqi Wang, Weifan Jiang, Asaf Cidon, Suman Jana

There are various costs for attackers to manipulate the features of security classifiers.

Spam detection

Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm

1 code implementation31 Jul 2019 Yihang Lou, Ling-Yu Duan, Yong Luo, Ziqian Chen, Tongliang Liu, Shiqi Wang, Wen Gao

The digital retina in smart cities is to select what the City Eye tells the City Brain, and convert the acquired visual data from front-end visual sensors to features in an intelligent sensing manner.

Intrinsic Image Popularity Assessment

1 code implementation3 Jul 2019 Keyan Ding, Kede Ma, Shiqi Wang

The goal of research in automatic image popularity assessment (IPA) is to develop computational models that can accurately predict the potential of a social image to go viral on the Internet.

Image popularity prediction

Towards Compact and Robust Deep Neural Networks

no code implementations14 Jun 2019 Vikash Sehwag, Shiqi Wang, Prateek Mittal, Suman Jana

In this work, we rigorously study the extension of network pruning strategies to preserve both benign accuracy and robustness of a network.

Adversarial Robustness Network Pruning

Enhancing Gradient-based Attacks with Symbolic Intervals

no code implementations5 Jun 2019 Shiqi Wang, Yizheng Chen, Ahmed Abdou, Suman Jana

In this paper, we present interval attacks, a new technique to find adversarial examples to evaluate the robustness of neural networks.

Open-Ended Question Answering

Masked Non-Autoregressive Image Captioning

no code implementations3 Jun 2019 Junlong Gao, Xi Meng, Shiqi Wang, Xia Li, Shanshe Wang, Siwei Ma, Wen Gao

Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens.

Image Captioning Machine Translation +1

On the Mathematical Understanding of ResNet with Feynman Path Integral

no code implementations16 Apr 2019 Minghao Yin, Xiu Li, Yongbing Zhang, Shiqi Wang

In this paper, we aim to understand Residual Network (ResNet) in a scientifically sound way by providing a bridge between ResNet and Feynman path integral.

Self-critical n-step Training for Image Captioning

no code implementations CVPR 2019 Junlong Gao, Shiqi Wang, Shanshe Wang, Siwei Ma, Wen Gao

Existing methods for image captioning are usually trained by cross entropy loss, which leads to exposure bias and the inconsistency between the optimizing function and evaluation metrics.

Image Captioning

Image and Video Compression with Neural Networks: A Review

no code implementations7 Apr 2019 Siwei Ma, Xinfeng Zhang, Chuanmin Jia, Zhenghui Zhao, Shiqi Wang, Shanshe Wang

Deep convolution neural network (CNN) which makes the neural network resurge in recent years and has achieved great success in both artificial intelligent and signal processing fields, also provides a novel and promising solution for image and video compression.

Video Compression

On Training Robust PDF Malware Classifiers

1 code implementation6 Apr 2019 Yizheng Chen, Shiqi Wang, Dongdong She, Suman Jana

A practically useful malware classifier must be robust against evasion attacks.

Scalable Facial Image Compression with Deep Feature Reconstruction

no code implementations14 Mar 2019 Shurun Wang, Shiqi Wang, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Wen Gao

In this paper, we propose a scalable image compression scheme, including the base layer for feature representation and enhancement layer for texture representation.

Image Compression

MixTrain: Scalable Training of Verifiably Robust Neural Networks

1 code implementation6 Nov 2018 Shiqi Wang, Yizheng Chen, Ahmed Abdou, Suman Jana

Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks.

Efficient Formal Safety Analysis of Neural Networks

2 code implementations NeurIPS 2018 Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana

Our approach can check different safety properties and find concrete counterexamples for networks that are 10$\times$ larger than the ones supported by existing analysis techniques.

Adversarial Attack Adversarial Defense +2

Intermediate Deep Feature Compression: the Next Battlefield of Intelligent Sensing

no code implementations17 Sep 2018 Zhuo Chen, Weisi Lin, Shiqi Wang, Ling-Yu Duan, Alex C. Kot

The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical.

Data Compression Feature Compression

Domain Generalization With Adversarial Feature Learning

no code implementations CVPR 2018 Haoliang Li, Sinno Jialin Pan, Shiqi Wang, Alex C. Kot

In this paper, we tackle the problem of domain generalization: how to learn a generalized feature representation for an “unseen” target domain by taking the advantage of multiple seen source-domain data.

Domain Generalization

Formal Security Analysis of Neural Networks using Symbolic Intervals

3 code implementations28 Apr 2018 Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana

In this paper, we present a new direction for formally checking security properties of DNNs without using SMT solvers.

Autonomous Vehicles

AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond

no code implementations5 Dec 2017 Ling-Yu Duan, Yihang Lou, Shiqi Wang, Wen Gao, Yong Rui

To practically facilitate deep neural network models in the large-scale video analysis, there are still unprecedented challenges for the large-scale video data management.


Spatial-Temporal Residue Network Based In-Loop Filter for Video Coding

no code implementations25 Sep 2017 Chuanmin Jia, Shiqi Wang, Xinfeng Zhang, Shanshe Wang, Siwei Ma

Deep learning has demonstrated tremendous break through in the area of image/video processing.


Image Quality Assessment Guided Deep Neural Networks Training

3 code implementations13 Aug 2017 Zhuo Chen, Weisi Lin, Shiqi Wang, Long Xu, Leida Li

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i. e., artifact-free).

Data Augmentation Image Classification +1

Compact Descriptors for Video Analysis: the Emerging MPEG Standard

no code implementations26 Apr 2017 Ling-Yu Duan, Vijay Chandrasekhar, Shiqi Wang, Yihang Lou, Jie Lin, Yan Bai, Tiejun Huang, Alex ChiChung Kot, Wen Gao

This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG).

Improving Object Detection with Region Similarity Learning

no code implementations1 Mar 2017 Feng Gao, Yihang Lou, Yan Bai, Shiqi Wang, Tiejun Huang, Ling-Yu Duan

Object detection aims to identify instances of semantic objects of a certain class in images or videos.

Multi-Task Learning object-detection +1

Incorporating Intra-Class Variance to Fine-Grained Visual Recognition

no code implementations1 Mar 2017 Yan Bai, Feng Gao, Yihang Lou, Shiqi Wang, Tiejun Huang, Ling-Yu Duan

In this paper, we propose to leverage intra-class variance in metric learning of triplet network to improve the performance of fine-grained recognition.

Fine-Grained Visual Recognition Metric Learning +1

Globally Variance-Constrained Sparse Representation and Its Application in Image Set Coding

no code implementations17 Aug 2016 Xiang Zhang, Jiarui Sun, Siwei Ma, Zhouchen Lin, Jian Zhang, Shiqi Wang, Wen Gao

Therefore, introducing an accurate rate-constraint in sparse coding and dictionary learning becomes meaningful, which has not been fully exploited in the context of sparse representation.

Data Compression Dictionary Learning

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