1 code implementation • 6 May 2024 • Xin Ding, Yongwei Wang, Kao Zhang, Z. Jane Wang
In this paper, we introduce Continuous Conditional Diffusion Models (CCDMs), the first CDM designed specifically for the CCGM task.
1 code implementation • 28 Mar 2024 • Mohsen Gholami, Mohammad Akbari, Cindy Hu, Vaden Masrani, Z. Jane Wang, Yong Zhang
Knowledge distillation from LLMs is essential for the efficient deployment of language models.
1 code implementation • 22 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.
1 code implementation • Medical Image Analysis 2023 • Mohsen Gholami, Rabab Ward, Ravneet Mahal, Maryam Mirian, Kevin Yen, Kye Won Park, Martin J. McKeown, Z. Jane Wang
The method obtained state-of-the-art results on the Human3. 6M dataset.
no code implementations • 8 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.
no code implementations • 12 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.
no code implementations • 10 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.
1 code implementation • 22 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.
1 code implementation • 15 Mar 2022 • Arvin Tashakori, Wenwen Zhang, Z. Jane Wang, Peyman Servati
In this work, edge users collaborate to train a Hyper-network in the server, generating personalized autoencoders for each user.
1 code implementation • CVPR 2022 • Mohsen Gholami, Bastian Wandt, Helge Rhodin, Rabab Ward, Z. Jane Wang
To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset and uses them to fine-tune a 3D pose estimator.
no code implementations • 8 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.
no code implementations • 6 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.
1 code implementation • 15 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.
no code implementations • 31 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.
no code implementations • 14 May 2021 • Mohsen Gholami, Ahmad Rezaei, Helge Rhodin, Rabab Ward, Z. Jane Wang
Estimating 3D human poses from video is a challenging problem.
Ranked #13 on Weakly-supervised 3D Human Pose Estimation on Human3.6M
2 code implementations • 7 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.
no code implementations • 24 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.
Ranked #7 on 3D Reconstruction on ShapeNet
1 code implementation • 20 Mar 2021 • Xin Ding, Yongwei Wang, Z. Jane Wang, William J. Welch
When sampling from CcGANs, the superiority of cDR-RS is even more noticeable in terms of both effectiveness and efficiency.
Ranked #1 on Image Generation on RC-49
no code implementations • 17 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.
no code implementations • 26 Jan 2021 • Mazen Abdelfattah, Kaiwen Yuan, Z. Jane Wang, Rabab Ward
We attack a prominent cascaded multi-modal DNN, the Frustum-Pointnet model.
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.
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).
Ranked #2 on Image Generation on RC-49
no code implementations • 30 Oct 2020 • Yongwei Wang, Mingquan Feng, Rabab Ward, Z. Jane Wang, Lanjun Wang
White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images.
1 code implementation • 29 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.
no code implementations • 5 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.
1 code implementation • 24 Sep 2019 • Xin Ding, Z. Jane Wang, William J. Welch
Our subsampling methods do not rely on the optimality of the discriminator and are suitable for all types of GANs.
no code implementations • 29 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}.
no code implementations • 7 Apr 2019 • Ramy Hussein, Mohamed Osama Ahmed, Rabab Ward, Z. Jane Wang, Levin Kuhlmann, Yi Guo
2) The traditional PCA is not a reliable method for iEEG data reduction in seizure prediction.
1 code implementation • 7 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.
no code implementations • 23 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.
no code implementations • 27 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.
no code implementations • 27 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.
no code implementations • 1 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.