Search Results for author: Yuhang Lu

Found 21 papers, 6 papers with code

Discriminative Deep Feature Visualization for Explainable Face Recognition

no code implementations1 Jun 2023 Zewei Xu, Yuhang Lu, Touradj Ebrahimi

To further interpret the decision of an FR model, a novel visual saliency explanation algorithm has been proposed.

Towards Visual Saliency Explanations of Face Recognition

no code implementations15 May 2023 Yuhang Lu, Zewei Xu, Touradj Ebrahimi

Deep convolutional neural networks have been pushing the frontier of face recognition (FR) techniques in the past years.

Decision Making Face Recognition

Explanation of Face Recognition via Saliency Maps

no code implementations12 Apr 2023 Yuhang Lu, Touradj Ebrahimi

Recent studies have explored use of visual saliency maps as an explanation, but they often lack a deeper analysis in the context of face recognition.

Decision Making Face Recognition

Assessment Framework for Deepfake Detection in Real-world Situations

no code implementations12 Apr 2023 Yuhang Lu, Touradj Ebrahimi

In this paper, a more reliable assessment framework is proposed to evaluate the performance of learning-based deepfake detectors in more realistic settings.

Data Augmentation DeepFake Detection +1

Impact of Video Processing Operations in Deepfake Detection

no code implementations30 Mar 2023 Yuhang Lu, Touradj Ebrahimi

Moreover, substantial experiments have been carried out on three popular deepfake detectors, which give detailed analyses on the impact of each operation and bring insights to foster future research.

DeepFake Detection Face Swapping

Identity-Preserving Knowledge Distillation for Low-resolution Face Recognition

no code implementations15 Mar 2023 Yuhang Lu, Touradj Ebrahimi

Low-resolution face recognition (LRFR) has become a challenging problem for modern deep face recognition systems.

Face Recognition Knowledge Distillation +1

Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint

1 code implementation6 Dec 2022 Hai Jiang, Haipeng Li, Yuhang Lu, Songchen Han, Shuaicheng Liu

Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field.

Homography Estimation

Cross-domain Few-shot Segmentation with Transductive Fine-tuning

no code implementations27 Nov 2022 Yuhang Lu, Xinyi Wu, Zhenyao Wu, Song Wang

Few-shot segmentation (FSS) expects models trained on base classes to work on novel classes with the help of a few support images.

Cross-Domain Few-Shot

A New Approach to Improve Learning-based Deepfake Detection in Realistic Conditions

no code implementations22 Mar 2022 Yuhang Lu, Touradj Ebrahimi

Extensive experiments show that the proposed data augmentation scheme improves generalization ability to unpredictable data distortions and unseen datasets.

Data Augmentation DeepFake Detection +1

Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation

1 code implementation9 Dec 2021 Xinyi Wu, Zhenyao Wu, Yuhang Lu, Lili Ju, Song Wang

In this paper, we tackle the problem of one-shot unsupervised domain adaptation (OSUDA) for semantic segmentation where the segmentors only see one unlabeled target image during training.

One-shot Unsupervised Domain Adaptation Semantic Segmentation +2

Impact of Benign Modifications on Discriminative Performance of Deepfake Detectors

no code implementations14 Nov 2021 Yuhang Lu, Evgeniy Upenik, Touradj Ebrahimi

Deepfakes are becoming increasingly popular in both good faith applications such as in entertainment and maliciously intended manipulations such as in image and video forgery.

DeepFake Detection Denoising +1

Contour Transformer Network for One-shot Segmentation of Anatomical Structures

1 code implementation2 Dec 2020 Yuhang Lu, Kang Zheng, Weijian Li, Yirui Wang, Adam P. Harrison, ChiHung Lin, Song Wang, Jing Xiao, Le Lu, Chang-Fu Kuo, Shun Miao

In this work, we present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism.

Anatomy One-Shot Learning +1

Does Haze Removal Help CNN-based Image Classification?

no code implementations ECCV 2018 Yanting Pei, Yaping Huang, Qi Zou, Yuhang Lu, Song Wang

Typically, the goal of image dehazing is to produce clearer images from which human vision can better identify the object and structural details present in the images.

Classification General Classification +3

Design Identification of Curve Patterns on Cultural Heritage Objects: Combining Template Matching and CNN-based Re-Ranking

no code implementations17 May 2018 Jun Zhou, Yuhang Lu, Kang Zheng, Karen Smith, Colin Wilder, Song Wang

The goal of this paper is to address the challenging problem of automatically identifying the underlying full design of curve patterns from such a sherd.

Re-Ranking Template Matching

Curve-Structure Segmentation from Depth Maps: A CNN-based Approach and Its Application to Exploring Cultural Heritage Objects

no code implementations7 Nov 2017 Yuhang Lu, Jun Zhou, Jing Wang, Jun Chen, Karen Smith, Colin Wilder, Song Wang

Motivated by the important archaeological application of exploring cultural heritage objects, in this paper we study the challenging problem of automatically segmenting curve structures that are very weakly stamped or carved on an object surface in the form of a highly noisy depth map.

Image Segmentation Semantic Segmentation

Scale-constrained Unsupervised Evaluation Method for Multi-scale Image Segmentation

1 code implementation15 Nov 2016 Yuhang Lu, Youchuan Wan, Gang Li

Unsupervised evaluation of segmentation quality is a crucial step in image segmentation applications.

Image Segmentation Semantic Segmentation

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