Search Results for author: Yuan-Gen Wang

Found 14 papers, 6 papers with code

Black-box Adversarial Attacks Against Image Quality Assessment Models

no code implementations27 Feb 2024 Yu Ran, Ao-Xiang Zhang, Mingjie Li, Weixuan Tang, Yuan-Gen Wang

Specifically, we first formulate the attack problem as maximizing the deviation between the estimated quality scores of original and perturbed images, while restricting the perturbed image distortions for visual quality preservation.

No-Reference Image Quality Assessment NR-IQA

CPDM: Content-Preserving Diffusion Model for Underwater Image Enhancement

no code implementations28 Jan 2024 Xiaowen Shi, Yuan-Gen Wang

In this article, we make the first attempt to adapt the diffusion model to the UIE task and propose a Content-Preserving Diffusion Model (CPDM) to address the above challenges.

UIE

Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks

1 code implementation NeurIPS 2023 Ao-Xiang Zhang, Yu Ran, Weixuan Tang, Yuan-Gen Wang

In this paper, we make the first attempt to evaluate the robustness of NR-VQA models against adversarial attacks, and propose a patch-based random search method for black-box attack.

Video Quality Assessment Visual Question Answering (VQA)

NLCUnet: Single-Image Super-Resolution Network with Hairline Details

no code implementations22 Jul 2023 Jiancong Feng, Yuan-Gen Wang, Fengchuang Xing

Based on this finding, we create a new network architecture by integrating depth-wise convolution with channel attention without the blur kernel estimation, resulting in a performance improvement instead.

Image Super-Resolution SSIM

Object-Attentional Untargeted Adversarial Attack

no code implementations16 Oct 2022 Chao Zhou, Yuan-Gen Wang, Guopu Zhu

Specifically, we first generate an object region by intersecting the object detection region from YOLOv4 with the salient object detection (SOD) region from HVPNet.

Adversarial Attack Object +3

HVS Revisited: A Comprehensive Video Quality Assessment Framework

no code implementations9 Oct 2022 Ao-Xiang Zhang, Yuan-Gen Wang, Weixuan Tang, Leida Li, Sam Kwong

Based on the revisited HVS, a no-reference VQA framework called HVS-5M (NRVQA framework with five modules simulating HVS with five characteristics) is proposed.

Video Quality Assessment Visual Question Answering (VQA)

Query-Efficient Adversarial Attack Based on Latin Hypercube Sampling

1 code implementation5 Jul 2022 Dan Wang, Jiayu Lin, Yuan-Gen Wang

However, existing BA methods craft adversarial examples by leveraging a simple random sampling (SRS) to estimate the gradient, consuming a large number of model queries.

Adversarial Attack

Multi-feature Co-learning for Image Inpainting

1 code implementation21 May 2022 Jiayu Lin, Yuan-Gen Wang, Wenzhi Tang, Aifeng Li

Then the proposed SDFF module integrates structure features into texture features, and meanwhile uses texture features as an auxiliary in generating structure features.

Image Inpainting

ADT-SSL: Adaptive Dual-Threshold for Semi-Supervised Learning

no code implementations21 May 2022 Zechen Liang, Yuan-Gen Wang, Wei Lu, Xiaochun Cao

Semi-Supervised Learning (SSL) has advanced classification tasks by inputting both labeled and unlabeled data to train a model jointly.

StarVQA: Space-Time Attention for Video Quality Assessment

no code implementations22 Aug 2021 Fengchuang Xing, Yuan-Gen Wang, Hanpin Wang, Leida Li, Guopu Zhu

To capture the long-range spatiotemporal dependencies of a video sequence, StarVQA encodes the space-time position information of each patch to the input of the Transformer.

Video Quality Assessment Visual Question Answering (VQA)

Fast Reinforcement Learning for Anti-jamming Communications

no code implementations13 Feb 2020 Pei-Gen Ye, Yuan-Gen Wang, Jin Li, Liang Xiao

This letter presents a fast reinforcement learning algorithm for anti-jamming communications which chooses previous action with probability $\tau$ and applies $\epsilon$-greedy with probability $(1-\tau)$.

reinforcement-learning Reinforcement Learning (RL)

Controllable List-wise Ranking for Universal No-reference Image Quality Assessment

1 code implementation24 Nov 2019 Fu-Zhao Ou, Yuan-Gen Wang, Jin Li, Guopu Zhu, Sam Kwong

First, to extend the authentically distorted image dataset, we present an imaging-heuristic approach, in which the over-underexposure is formulated as an inverse of Weber-Fechner law, and fusion strategy and probabilistic compression are adopted, to generate the degraded real-world images.

No-Reference Image Quality Assessment NR-IQA

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