Search Results for author: Pengxu Wei

Found 20 papers, 12 papers with code

Cross-modal Contrastive Attention Model for Medical Report Generation

no code implementations COLING 2022 Xiao Song, Xiaodan Zhang, Junzhong Ji, Ying Liu, Pengxu Wei

Medical report automatic generation has gained increasing interest recently as a way to help radiologists write reports more efficiently.

Medical Report Generation

Towards Real-World Burst Image Super-Resolution: Benchmark and Method

1 code implementation9 Sep 2023 Pengxu Wei, Yujing Sun, Xingbei Guo, Chang Liu, Jie Chen, Xiangyang Ji, Liang Lin

Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios.

Burst Image Super-Resolution

Identity-Preserving Talking Face Generation with Landmark and Appearance Priors

1 code implementation CVPR 2023 Weizhi Zhong, Chaowei Fang, Yinqi Cai, Pengxu Wei, Gangming Zhao, Liang Lin, Guanbin Li

Prior landmark characteristics of the speaker's face are employed to make the generated landmarks coincide with the facial outline of the speaker.

Talking Face Generation

Masked Images Are Counterfactual Samples for Robust Fine-tuning

1 code implementation CVPR 2023 Yao Xiao, Ziyi Tang, Pengxu Wei, Cong Liu, Liang Lin

In this paper, based on causal analysis of the aforementioned problems, we propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.

DQnet: Cross-Model Detail Querying for Camouflaged Object Detection

no code implementations16 Dec 2022 Wei Sun, Chengao Liu, Linyan Zhang, Yu Li, Pengxu Wei, Chang Liu, Jialing Zou, Jianbin Jiao, Qixiang Ye

Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue which inevitably leads to missing or redundant regions of objects.

object-detection Object Detection +1

DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Positive-Negative Prompt-Tuning

no code implementations21 Nov 2022 Ziyi Dong, Pengxu Wei, Liang Lin

Although recent attempts have employed fine-tuning or prompt-tuning strategies to teach the pre-trained diffusion model novel concepts from a reference image set, they have the drawback of overfitting to the given reference images, particularly in one-shot applications, which is harmful to generate diverse and high-quality images while maintaining generation controllability.

Novel Concepts

Robust Real-World Image Super-Resolution against Adversarial Attacks

1 code implementation31 Jul 2022 Jiutao Yue, Haofeng Li, Pengxu Wei, Guanbin Li, Liang Lin

Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module.

Image Super-Resolution

Adversarially-Aware Robust Object Detector

1 code implementation13 Jul 2022 Ziyi Dong, Pengxu Wei, Liang Lin

In this work, we empirically explore the model training for adversarial robustness in object detection, which greatly attributes to the conflict between learning clean images and adversarial images.

Adversarial Robustness object-detection +1

Real-World Image Super-Resolution by Exclusionary Dual-Learning

1 code implementation6 Jun 2022 Hao Li, Jinghui Qin, Zhijing Yang, Pengxu Wei, Jinshan Pan, Liang Lin, Yukai Shi

Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attention with regard to its tremendous application potentials.

Image Restoration Image Super-Resolution

Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

1 code implementation CVPR 2022 Xiaoqian Xu, Pengxu Wei, Weikai Chen, Mingzhi Mao, Liang Lin, Guanbin Li

To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera.

Image Super-Resolution Unsupervised Domain Adaptation

Open Set Domain Adaptation By Novel Class Discovery

no code implementations7 Mar 2022 Jingyu Zhuang, Ziliang Chen, Pengxu Wei, Guanbin Li, Liang Lin

In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain.

Domain Adaptation Novel Class Discovery

Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning

no code implementations ICCV 2021 Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai, Xiaolin Wei, Pengxu Wei, Liang Lin, Guanbin Li

Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.

Binary Classification

CDNet: Centripetal Direction Network for Nuclear Instance Segmentation

2 code implementations ICCV 2021 Hongliang He, Zhongyi Huang, Yao Ding, Guoli Song, Lin Wang, Qian Ren, Pengxu Wei, Zhiqiang Gao, Jie Chen

Specifically, we define the centripetal direction feature as a class of adjacent directions pointing to the nuclear center to represent the spatial relationship between pixels within the nucleus.

Instance Segmentation Semantic Segmentation

Component Divide-and-Conquer for Real-World Image Super-Resolution

1 code implementation ECCV 2020 Pengxu Wei, Ziwei Xie, Hannan Lu, Zongyuan Zhan, Qixiang Ye, WangMeng Zuo, Liang Lin

Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures.

Image Super-Resolution

A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models

no code implementations31 Oct 2019 Yang Wu, Pengxu Wei, Liang Lin

To solve this problem, we derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation.

Min-Entropy Latent Model for Weakly Supervised Object Detection

1 code implementation CVPR 2018 Fang Wan, Pengxu Wei, Zhenjun Han, Jianbin Jiao, Qixiang Ye

Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors.

Image Classification object-detection +2

3D Human Pose Machines with Self-supervised Learning

2 code implementations 2019 Keze Wang, Liang Lin, Chenhan Jiang, Chen Qian, Pengxu Wei

Driven by recent computer vision and robotic applications, recovering 3D human poses has become increasingly important and attracted growing interests.

3D Human Pose Estimation Self-Supervised Learning

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