405 citations · 2.3k across the 116 of their papers we have counts for
68 papers · 1 filter
Unsupervised Green Object Tracker (GOT) without Offline Pre-training
Zhiruo Zhou, Suya You, C. -C. Jay Kuo
Supervised trackers trained on labeled data dominate the single object tracking field for superior tracking accuracy. The labeling cost and the huge computational complexity hinder…
Lightweight Image Codec via Multi-Grid Multi-Block-Size Vector Quantization (MGBVQ)
Yifan Wang, Zhanxuan Mei, Ioannis Katsavounidis +1
A multi-grid multi-block-size vector quantization (MGBVQ) method is proposed for image coding in this work. The fundamental idea of image coding is to remove correlations among pix…
MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust Classifier
Mozhdeh Rouhsedaghat, Masoud Monajatipoor, C. -C. Jay Kuo +1
We offer a method for one-shot mask-guided image synthesis that allows controlling manipulations of a single image by inverting a quasi-robust classifier equipped with strong regul…
Unsupervised Domain Adaptation for Segmentation with Black-box Source Model
Xiaofeng Liu, Chaehwa Yoo, Fangxu Xing +3
Unsupervised domain adaptation (UDA) has been widely used to transfer knowledge from a labeled source domain to an unlabeled target domain to counter the difficulty of labeling in…
Subtype-Aware Dynamic Unsupervised Domain Adaptation
Xiaofeng Liu, Fangxu Xing, Jia You +4
Unsupervised domain adaptation (UDA) has been successfully applied to transfer knowledge from a labeled source domain to target domains without their labels. Recently introduced tr…
Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics
Xiaoyuan Guo, Jiali Duan, C. -C. Jay Kuo +2
Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning. In contrast, visual mo…
Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking
Yijing Yang, Hongyu Fu, C. -C. Jay Kuo
The design of robust learning systems that offer stable performance under a wide range of supervision degrees is investigated in this work. We choose the image classification probl…
ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-training
Xiaofeng Liu, Fangxu Xing, Nadya Shusharina +4
Unsupervised domain adaptation (UDA) has been vastly explored to alleviate domain shifts between source and target domains, by applying a well-performed model in an unlabeled targe…
PAGER: Progressive Attribute-Guided Extendable Robust Image Generation
Zohreh Azizi, C. -C. Jay Kuo
This work presents a generative modeling approach based on successive subspace learning (SSL). Unlike most generative models in the literature, our method does not utilize neural n…
A-PixelHop: A Green, Robust and Explainable Fake-Image Detector
Yao Zhu, Xinyu Wang, Hong-Shuo Chen +2
A novel method for detecting CNN-generated images, called Attentive PixelHop (or A-PixelHop), is proposed in this work. It has three advantages: 1) low computational complexity and…
Unsupervised Lightweight Single Object Tracking with UHP-SOT++
Zhiruo Zhou, Hongyu Fu, Suya You +1
An unsupervised, lightweight and high-performance single object tracker, called UHP-SOT, was proposed by Zhou et al. recently. As an extension, we present an enhanced version and n…
PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimation
Kaitai Zhang, Bin Wang, C. -C. Jay Kuo
A neural network targeting at unsupervised image anomaly localization, called the PEDENet, is proposed in this work. PEDENet contains a patch embedding (PE) network, a density esti…
UHP-SOT: An Unsupervised High-Performance Single Object Tracker
Zhiruo Zhou, Hongyu Fu, Suya You +2
An unsupervised online object tracking method that exploits both foreground and background correlations is proposed and named UHP-SOT (Unsupervised High-Performance Single Object T…
BERTHop: An Effective Vision-and-Language Model for Chest X-ray Disease Diagnosis
Masoud Monajatipoor, Mozhdeh Rouhsedaghat, Liunian Harold Li +4
Vision-and-language(V&L) models take image and text as input and learn to capture the associations between them. Prior studies show that pre-trained V&L models can significantly im…
Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate
Xiaofeng Liu, Zhenhua Guo, Site Li +5
In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r…
Bridging Gap between Image Pixels and Semantics via Supervision: A Survey
Jiali Duan, C. -C. Jay Kuo
The fact that there exists a gap between low-level features and semantic meanings of images, called the semantic gap, is known for decades. Resolution of the semantic gap is a long…
Evaluation of Multimodal Semantic Segmentation using RGB-D Data
Jiesi Hu, Ganning Zhao, Suya You +1
Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environ…
R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method
Pranav Kadam, Min Zhang, Shan Liu +1
Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work. R-PointHop first determines…
Successive Subspace Learning: An Overview
Mozhdeh Rouhsedaghat, Masoud Monajatipoor, Zohreh Azizi +1
Successive Subspace Learning (SSL) offers a light-weight unsupervised feature learning method based on inherent statistical properties of data units (e.g. image pixels and points i…
SLADE: A Self-Training Framework For Distance Metric Learning
Jiali Duan, Yen-Liang Lin, Son Tran +2
Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to imp…
Noise-Aware Texture-Preserving Low-Light Enhancement
Zohreh Azizi, Xuejing Lei, C. -C Jay Kuo
A simple and effective low-light image enhancement method based on a noise-aware texture-preserving retinex model is proposed in this work. The new method, called NATLE, attempts t…
FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method
Mozhdeh Rouhsedaghat, Yifan Wang, Xiou Ge +3
A light-weight low-resolution face gender classification method, called FaceHop, is proposed in this research. We have witnessed rapid progress in face gender classification accura…
PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification
Min Zhang, Yifan Wang, Pranav Kadam +2
The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction. It has an extremely low training complexity while…
Towards Disentangled Representations for Human Retargeting by Multi-view Learning
Chao Yang, Xiaofeng Liu, Qingming Tang +1
We study the problem of learning disentangled representations for data across multiple domains and its applications in human retargeting. Our goal is to map an input image to an id…