Search Results for author: Mingyang Ma

Found 8 papers, 2 papers with code

User Satisfaction Modeling with Domain Adaptation in Task-oriented Dialogue Systems

no code implementations SIGDIAL (ACL) 2022 Yan Pan, Mingyang Ma, Bernhard Pflugfelder, Georg Groh

To the best of our knowledge, this is the first work to study user satisfaction estimation with unsupervised domain adaptation from chitchat to task-oriented dialogue.

Action Recognition Task-Oriented Dialogue Systems +1

A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking

no code implementations21 Jun 2023 Shaohui Mei, Jiawei Lian, Xiaofei Wang, Yuru Su, Mingyang Ma, Lap-Pui Chau

Surprisingly, there has been a lack of comprehensive studies on the robustness of RS tasks, prompting us to undertake a thorough survey and benchmark on the robustness of image classification and object detection in RS.

Adversarial Robustness Benchmarking +3

CBA: Contextual Background Attack against Optical Aerial Detection in the Physical World

1 code implementation27 Feb 2023 Jiawei Lian, Xiaofei Wang, Yuru Su, Mingyang Ma, Shaohui Mei

To further strengthen the attack performance, the adversarial patches are forced to be outside targets during training, by which the detected objects of interest, both on and outside patches, benefit the accumulation of attack efficacy.

Adversarial Robustness

Contextual adversarial attack against aerial detection in the physical world

no code implementations27 Feb 2023 Jiawei Lian, Xiaofei Wang, Yuru Su, Mingyang Ma, Shaohui Mei

We propose an innovative contextual attack method against aerial detection in real scenarios, which achieves powerful attack performance and transfers well between various aerial object detectors without smearing or blocking the interested objects to hide.

Adversarial Attack Blocking

Benchmarking Adversarial Patch Against Aerial Detection

1 code implementation30 Oct 2022 Jiawei Lian, Shaohui Mei, Shun Zhang, Mingyang Ma

DNNs are vulnerable to adversarial examples, which poses great security concerns for security-critical systems.

Benchmarking

How to Build Robust FAQ Chatbot with Controllable Question Generator?

no code implementations18 Nov 2021 Yan Pan, Mingyang Ma, Bernhard Pflugfelder, Georg Groh

Many unanswerable adversarial questions fool the question-answer (QA) system with some plausible answers.

Chatbot Passage Retrieval +4

Spectral Variability Augmented Sparse Unmixing of Hyperspectral Images

no code implementations19 Oct 2021 Ge Zhang, Shaohui Mei, Mingyang Ma, Yan Feng, Qian Du

Spectral unmixing (SU) expresses the mixed pixels existed in hyperspectral images as the product of endmember and abundance, which has been widely used in hyperspectral imagery analysis.

Spectral Reconstruction

Compressive Shack-Hartmann Wavefront Sensor based on Deep Neural Networks

no code implementations20 Nov 2020 Peng Jia, Mingyang Ma, Dongmei Cai, Weihua Wang, Juanjuan Li, Can Li

However if there exists strong atmospheric turbulence or the brightness of guide stars is low, the accuracy of wavefront measurements will be affected.

Compressive Sensing Image Deconvolution +1

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