no code implementations • 20 Mar 2024 • Yifan Wu, Jiawei Du, Ping Liu, Yuewei Lin, Wenqing Cheng, Wei Xu
Dataset distillation is an advanced technique aimed at compressing datasets into significantly smaller counterparts, while preserving formidable training performance.
no code implementations • 8 Mar 2024 • Huiming Sun, Jiacheng Guo, Zibo Meng, Tianyun Zhang, Jianwu Fang, Yuewei Lin, Hongkai Yu
One white-box and two black-box patch based attack methods are implemented to attack three classic deep neural networks based object detectors on EVD4UAV.
1 code implementation • 10 Dec 2023 • Joonwoo Kwon, Sooyoung Kim, Yuewei Lin, Shinjae Yoo, Jiook Cha
The primary idea is to decompose the image via its frequencies to better disentangle aesthetic styles from the reference image while training the entire model in an end-to-end manner to exclude pre-trained models at inference completely.
no code implementations • 4 Oct 2023 • Haotian Liu, Zhiqing Wei, Fengyun Li, Yuewei Lin, Hanyang Qu, Huici Wu, Zhiyong Feng
The ISAC-enabled mobile communication system regularly operate in non-continuous spectrum bands due to crowded licensed frequency bands.
no code implementations • 9 Sep 2023 • Hong Wang, Yuefan Deng, Shinjae Yoo, Yuewei Lin
In this paper, we strive to explore the robust features which are not affected by the adversarial perturbations, i. e., invariant to the clean image and its adversarial examples, to improve the model's adversarial robustness.
no code implementations • 8 Sep 2023 • Xi Yu, Huan-Hsin Tseng, Shinjae Yoo, Haibin Ling, Yuewei Lin
Specifically, we first propose an information theory inspired loss function to ensure the disentangled class-relevant features contain sufficient class label information and the other disentangled auxiliary feature has sufficient domain information.
no code implementations • 30 Jun 2023 • Huiming Sun, Lan Fu, Jinlong Li, Qing Guo, Zibo Meng, Tianyun Zhang, Yuewei Lin, Hongkai Yu
Furthermore, we design DefenseNet as a learn-able pre-processing to the adversarial cloudy images so as to preserve the performance of the deep learning based remote sensing SOD model, without tuning the already deployed deep SOD model.
no code implementations • 22 Jun 2023 • Jin Ma, Jinlong Li, Qing Guo, Tianyun Zhang, Yuewei Lin, Hongkai Yu
The emergence of different sensors (Near-Infrared, Depth, etc.)
no code implementations • 20 Nov 2022 • Huiming Sun, Jin Ma, Qing Guo, Qin Zou, Shaoyue Song, Yuewei Lin, Hongkai Yu
To the best of our knowledge, all the existing image inpainting algorithms learn to repair the occluded regions for a better visualization quality, they are excellent for natural images but not good enough for geoscience images by ignoring the geoscience related tasks.
1 code implementation • ICCV 2021 • Hong Wang, Yuefan Deng, Shinjae Yoo, Haibin Ling, Yuewei Lin
The attention knowledge is obtained from a weight-fixed model trained on a clean dataset, referred to as a teacher model, and transferred to a model that is under training on adversarial examples (AEs), referred to as a student model.
no code implementations • 20 Jun 2021 • Ping Liu, Yuewei Lin, Yang He, Yunchao Wei, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh, Jingen Liu
In this paper, we propose to utilize Automated Machine Learning to adaptively search a neural architecture for deepfake detection.
no code implementations • ICCV 2021 • Heng Fan, Halady Akhilesha Miththanthaya, Harshit, Siranjiv Ramana Rajan, Xiaoqiong Liu, Zhilin Zou, Yuewei Lin, Haibin Ling
To the best of our knowledge, TOTB is the first benchmark dedicated to transparent object tracking.
no code implementations • 26 Aug 2020 • Ping Liu, Yuewei Lin, Zibo Meng, Lu Lu, Weihong Deng, Joey Tianyi Zhou, Yi Yang
In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition.
no code implementations • 17 Jan 2020 • Heyi Li, Yuewei Lin, Klaus Mueller, Wei Xu
Using the Galaxy Zoo dataset we demonstrate that our method clearly reveals attention areas of the Discriminator when differentiating generated galaxy images from ground truth images.
1 code implementation • 8 Mar 2018 • Zheng Zhang, Qin Zou, Yuewei Lin, Long Chen, Song Wang
In this paper, a new deep hashing method is proposed for multi-label image retrieval by re-defining the pairwise similarity into an instance similarity, where the instance similarity is quantified into a percentage based on the normalized semantic labels.
no code implementations • ICCV 2017 • Kang Zheng, Xiaochuan Fan, Yuewei Lin, Hao Guo, Hongkai Yu, Dazhou Guo, Song Wang
In this paper, we attempt to utilize 3D human-skeleton sequences to learn a model that can extract view-invariant motion features from optical flows in different views.
no code implementations • CVPR 2016 • Hongkai Yu, Youjie Zhou, Jeff Simmons, Craig P. Przybyla, Yuewei Lin, Xiaochuan Fan, Yang Mi, Song Wang
In particular, the within-group association is modeled by a nonrigid 2D Thin-Plate transform and a sequence of group shrinking, group growing and group merging operations are then developed to refine the composition of each group.
no code implementations • 5 Sep 2015 • Yuewei Lin, Jing Chen, Yu Cao, Youjie Zhou, Lingfeng Zhang, Yuan Yan Tang, Song Wang
By adopting a natural and widely used assumption -- "the data samples from the same class should lay on a low-dimensional subspace, even if they come from different domains", the proposed method circumvents the limitation of the global domain shift, and solves the cross-domain recognition by finding the compact joint subspaces of source and target domain.
no code implementations • ICCV 2015 • Yuewei Lin, Kareem Ezzeldeen, Youjie Zhou, Xiaochuan Fan, Hongkai Yu, Hui Qian, Song Wang
Wearable cameras, such as Google Glass and Go Pro, enable video data collection over larger areas and from different views.
no code implementations • 11 Jul 2015 • Hongkai Yu, Youjie Zhou, Hui Qian, Min Xian, Yuewei Lin, Dazhou Guo, Kang Zheng, Kareem Abdelfatah, Song Wang
In this paper, we develop a new LooseCut algorithm that can handle cases where the input bounding box only loosely covers the foreground object.
1 code implementation • CVPR 2015 • Xiaochuan Fan, Kang Zheng, Yuewei Lin, Song Wang
We propose a new learning-based method for estimating 2D human pose from a single image, using Dual-Source Deep Convolutional Neural Networks (DS-CNN).
no code implementations • CVPR 2013 • Yu Cao, Daniel Barrett, Andrei Barbu, Siddharth Narayanaswamy, Haonan Yu, Aaron Michaux, Yuewei Lin, Sven Dickinson, Jeffrey Mark Siskind, Song Wang
In this paper, we propose a new method that can recognize human activities from partially observed videos in the general case.