Search Results for author: Z. Jane Wang

Found 31 papers, 12 papers with code

PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF

1 code implementation22 Dec 2023 Mohsen Gholami, Rabab Ward, Z. Jane Wang

The objective of PoseGen is to learn a distribution of data that maximizes the prediction error of a given pre-trained model.

Occlusion-Robust FAU Recognition by Mining Latent Space of Masked Autoencoders

no code implementations8 Dec 2022 Minyang Jiang, Yongwei Wang, Martin J. McKeown, Z. Jane Wang

Bypassing the occlusion reconstruction step, our model efficiently extracts FAU features of occluded faces by mining the latent space of a pretrained masked autoencoder.

Knowledge Distillation

Multi-modal Streaming 3D Object Detection

no code implementations12 Sep 2022 Mazen Abdelfattah, Kaiwen Yuan, Z. Jane Wang, Rabab Ward

Recent streaming perception works proposed directly processing LiDAR slices and compensating for the narrow field of view (FOV) of a slice by reusing features from preceding slices.

3D Object Detection Autonomous Vehicles +3

Generalizable Neural Radiance Fields for Novel View Synthesis with Transformer

no code implementations10 Jun 2022 Dan Wang, Xinrui Cui, Septimiu Salcudean, Z. Jane Wang

We propose a Transformer-based NeRF (TransNeRF) to learn a generic neural radiance field conditioned on observed-view images for the novel view synthesis task.

Neural Rendering Novel View Synthesis

SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images

1 code implementation22 Mar 2022 Yongwei Wang, Yuheng Wang, Tim K. Lee, Chunyan Miao, Z. Jane Wang

In this case, knowledge distillation (KD) has been proven as an efficient tool to help improve the adaptability of lightweight models under limited resources, meanwhile keeping a high-level representation capability.

Knowledge Distillation Lesion Classification +1

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey

no code implementations8 Dec 2021 Xun Chen, Chang Li, Aiping Liu, Martin J. McKeown, Ruobing Qian, Z. Jane Wang

Electroencephalogram (EEG) decoding aims to identify the perceptual, semantic, and cognitive content of neural processing based on non-invasively measured brain activity.

EEG Eeg Decoding

Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification

no code implementations6 Sep 2021 Jianzhe Lin, Tianze Yu, Z. Jane Wang

To address such concerns, we have a rethinking of crowdsourcing annotations: Our simple hypothesis is that if the annotators only partially annotate multi-label images with salient labels they are confident in, there will be fewer annotation errors and annotators will spend less time on uncertain labels.

Active Learning Multi-Label Image Classification

SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images

1 code implementation15 Aug 2021 Tianze Yu, Jianzhe Lin, Lichao Mou, Yuansheng Hua, Xiaoxiang Zhu, Z. Jane Wang

In our experiments, trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, the proposed model is tested directly on our collected Multi-scene Aerial Image (MAI) dataset.

Multi-Label Image Classification Multi-Label Learning +1

Delving into Deep Image Prior for Adversarial Defense: A Novel Reconstruction-based Defense Framework

no code implementations31 Jul 2021 Li Ding, Yongwei Wang, Xin Ding, Kaiwen Yuan, Ping Wang, Hua Huang, Z. Jane Wang

Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images.

Adversarial Defense Image Classification +1

Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression

2 code implementations7 Apr 2021 Xin Ding, Yongwei Wang, Zuheng Xu, Z. Jane Wang, William J. Welch

Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student based on the knowledge from a teacher.

General Classification Image Classification +2

Multi-view 3D Reconstruction with Transformer

no code implementations24 Mar 2021 Dan Wang, Xinrui Cui, Xun Chen, Zhengxia Zou, Tianyang Shi, Septimiu Salcudean, Z. Jane Wang, Rabab Ward

Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network.

3D Object Reconstruction 3D Reconstruction +1

Adversarial Attacks on Camera-LiDAR Models for 3D Car Detection

no code implementations17 Mar 2021 Mazen Abdelfattah, Kaiwen Yuan, Z. Jane Wang, Rabab Ward

The dense RGB input contributed more to the success of the adversarial attacks on both cascaded and fusion models.

Adversarial Attack Autonomous Vehicles

Multi-View 3D Reconstruction With Transformers

no code implementations ICCV 2021 Dan Wang, Xinrui Cui, Xun Chen, Zhengxia Zou, Tianyang Shi, Septimiu Salcudean, Z. Jane Wang, Rabab Ward

Unlike previous CNN-based methods using a separate design, we unify the feature extraction and view fusion in a single Transformer network.

3D Object Reconstruction 3D Reconstruction +1

Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms

1 code implementation ICLR 2021 Xin Ding, Yongwei Wang, Zuheng Xu, William J. Welch, Z. Jane Wang

This work proposes the continuous conditional generative adversarial network (CcGAN), the first generative model for image generation conditional on continuous, scalar conditions (termed regression labels).

Generative Adversarial Network Image Generation +1

Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection

1 code implementation29 Oct 2020 Yongwei Wang, Xin Ding, Li Ding, Rabab Ward, Z. Jane Wang

Specially, when adversaries consider imperceptibility as a constraint, the proposed anti-forensic method can improve the average attack success rate by around 30\% on fake face images over two baseline attacks.

Adversarial Attack Face Detection

CHAIN: Concept-harmonized Hierarchical Inference Interpretation of Deep Convolutional Neural Networks

no code implementations5 Feb 2020 Dan Wang, Xinrui Cui, Z. Jane Wang

For net-decisions being interpreted, the proposed method presents the CHAIN interpretation in which the net decision can be hierarchically deduced into visual concepts from high to low semantic levels.

Decision Making

A Deep Learning Based Attack for The Chaos-based Image Encryption

no code implementations29 Jul 2019 Chen He, Kan Ming, Yongwei Wang, Z. Jane Wang

In this letter, as a proof of concept, we propose a deep learning-based approach to attack the chaos-based image encryption algorithm in \cite{guan2005chaos}.

CHIP: Channel-wise Disentangled Interpretation of Deep Convolutional Neural Networks

1 code implementation7 Feb 2019 Xinrui Cui, Dan Wang, Z. Jane Wang

In this work, we propose a CHannel-wise disentangled InterPretation (CHIP) model to give the visual interpretation to the predictions of DCNNs.

Image Classification

DT-LET: Deep Transfer Learning by Exploring where to Transfer

no code implementations23 Sep 2018 Jianzhe Lin, Qi. Wang, Rabab Ward, Z. Jane Wang

Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains.

Transfer Learning

Multimodal deep learning approach for joint EEG-EMG data compression and classification

no code implementations27 Mar 2017 Ahmed Ben Said, Amr Mohamed, Tarek Elfouly, Khaled Harras, Z. Jane Wang

In this paper, we present a joint compression and classification approach of EEG and EMG signals using a deep learning approach.

Data Compression EEG +3

Real-time 2D/3D Registration via CNN Regression

no code implementations27 Jul 2015 Shun Miao, Z. Jane Wang, Rui Liao

In this paper, we present a Convolutional Neural Network (CNN) regression approach for real-time 2-D/3-D registration.

Computational Efficiency regression

An Adaptive Descriptor Design for Object Recognition in the Wild

no code implementations1 May 2013 Zhenyu Guo, Z. Jane Wang

These 'picture styles' are directly related to the scene radiance, image pipeline of the camera, and post processing functions.

Domain Adaptation Object +1

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