no code implementations • 29 Feb 2024 • Jingyi Liao, Xun Xu, Manh Cuong Nguyen, Adam Goodge, Chuan Sheng Foo
few-shot anomaly detection (FSAD).
no code implementations • 10 Jan 2024 • Nanqing Liu, Xun Xu, Yongyi Su, Chengxin Liu, Peiliang Gong, Heng-Chao Li
Domain adaptation is crucial in aerial imagery, as the visual representation of these images can significantly vary based on factors such as geographic location, time, and weather conditions.
1 code implementation • 6 Dec 2023 • Haojie Zhang, Yongyi Su, Xun Xu, Kui Jia
The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering.
no code implementations • 9 Oct 2023 • Nanqing Liu, Xun Xu, Yingjie Gao, Heng-Chao Li
Semi-supervised object detection (SSOD) methods tackle this issue by generating pseudo-labels for the unlabeled data, assuming that all classes found in the unlabeled dataset are also represented in the labeled data.
1 code implementation • 26 Sep 2023 • Yongyi Su, Xun Xu, Kui Jia
Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions.
1 code implementation • ICCV 2023 • Yushu Li, Xun Xu, Yongyi Su, Kui Jia
Existing approaches often focus on improving test-time training performance under well-curated target domain data.
no code implementations • 31 Mar 2023 • Yijin Chen, Xun Xu, Yongyi Su, Kui Jia
This motivates us to explore adapting an object detection model at test-time, a. k. a.
no code implementations • 20 Mar 2023 • Yongyi Su, Xun Xu, Tianrui Li, Kui Jia
Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available, and instant inference on the target domain is required.
no code implementations • 13 Mar 2023 • Nanqing Liu, Xun Xu, Turgay Celik, Zongxin Gan, Heng-Chao Li
Object detection in remote sensing images relies on a large amount of labeled data for training.
no code implementations • 14 Dec 2022 • Le Zhang, Qibin Hou, Yun Liu, Jia-Wang Bian, Xun Xu, Joey Tianyi Zhou, Ce Zhu
Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm.
1 code implementation • 6 Jun 2022 • Yongyi Su, Xun Xu, Kui Jia
Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required.
1 code implementation • 18 May 2022 • Xun Xu, Manh Cuong Nguyen, Yasin Yazici, Kangkang Lu, Hlaing Min, Chuan-Sheng Foo
In this work, we propose SemiCurv, a semi-supervised learning (SSL) framework for curvilinear structure segmentation that is able to utilize such unlabelled data to reduce the labelling burden.
no code implementations • 16 May 2022 • Zhihao Liang, Xun Xu, Shengheng Deng, Lile Cai, Tao Jiang, Kui Jia
3D object detection has recently received much attention due to its great potential in autonomous vehicle (AV).
no code implementations • 6 May 2022 • Yongyi Su, Xun Xu, Kui Jia
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning.
no code implementations • 6 May 2022 • Xun Xu, Jingyi Liao, Lile Cai, Manh Cuong Nguyen, Kangkang Lu, Wanyue Zhang, Yasin Yazici, Chuan Sheng Foo
Recent studies combined finetuning (FT) from pretrained weights with SSL to mitigate the challenges and claimed superior results in the low-label regime.
no code implementations • 2 May 2022 • Xian Shi, Xun Xu, Wanyue Zhang, Xiatian Zhu, Chuan Sheng Foo, Kui Jia
We also demonstrate the feasibility of a more efficient training strategy.
1 code implementation • 11 Dec 2021 • Wanyue Zhang, Xun Xu, Fayao Liu, Chuan-Sheng Foo
Data augmentation is an important technique to reduce overfitting and improve learning performance, but existing works on data augmentation for 3D point cloud data are based on heuristics.
Ranked #1 on 3D Point Cloud Data Augmentation on ModelNet40
no code implementations • 29 Sep 2021 • Cuong Manh Nguyen, Le Zhang, Arun Raja, Xun Xu, Balagopal Unnikrishnan, Kangkang Lu, Chuan-Sheng Foo
Label collection is costly in many applications, which poses the need for label-efficient learning.
no code implementations • CVPR 2021 • Lile Cai, Xun Xu, Jun Hao Liew, Chuan Sheng Foo
Our results strongly argue for the use of superpixel-based AL for semantic segmentation and highlight the importance of using realistic annotation costs in evaluating such methods.
1 code implementation • CVPR 2021 • Shengheng Deng, Xun Xu, Chaozheng Wu, Ke Chen, Kui Jia
The ability to understand the ways to interact with objects from visual cues, a. k. a.
Ranked #1 on Affordance Detection on 3D AffordanceNet
no code implementations • 9 Mar 2021 • Jieneng Chen, Ke Yan, Yu-Dong Zhang, YouBao Tang, Xun Xu, Shuwen Sun, Qiuping Liu, Lingyun Huang, Jing Xiao, Alan L. Yuille, Ya zhang, Le Lu
(2) The sampled deep vertex features with positional embedding are mapped into a sequential space and decoded by a multilayer perceptron (MLP) for semantic classification.
1 code implementation • 9 Feb 2021 • Jiaxuan Li, Peiyao Jin, Jianfeng Zhu, Haidong Zou, Xun Xu, Min Tang, Minwen Zhou, Yu Gan, Jiangnan He, Yuye Ling, Yikai Su
An accurate and automated tissue segmentation algorithm for retinal optical coherence tomography (OCT) images is crucial for the diagnosis of glaucoma.
no code implementations • 18 Jan 2021 • Xian Shi, Xun Xu, Ke Chen, Lile Cai, Chuan Sheng Foo, Kui Jia
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets.
no code implementations • ICLR 2021 • Kangkang Lu, Cuong Manh Nguyen, Xun Xu, Kiran Chari, Yu Jing Goh, Chuan-Sheng Foo
In this paper, we propose ARMOURED, an adversarially robust training method based on semi-supervised learning that consists of two components.
no code implementations • 14 Dec 2020 • Chaozheng Wu, Lin Sun, Xun Xu, Kui Jia
Given the large shape variations among different instances of a same category, we are formally interested in developing a quantity defined for individual points on a continuous object surface; the quantity specifies how individual surface points contribute to the formation of the shape as the category.
1 code implementation • CVPR 2020 • Xun Xu, Gim Hee Lee
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks.
1 code implementation • 8 Apr 2020 • Xun Xu, Gim Hee Lee
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks.
no code implementations • 16 Aug 2019 • Xun Xu, Loong-Fah Cheong, Zhuwen Li
Many real-world video sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation on video sequences would lead to difficulty.
no code implementations • 16 Aug 2019 • Xun Xu, Shaogang Gong, Timothy Hospedales
To that end, we relax the common assumption that each individual crowd video instance is only associated with a single crowd attribute.
1 code implementation • CVPR 2019 • Chao Zhang, Shuaicheng Liu, Xun Xu, Ce Zhu
Recently, MobileNets and ShuffleNets have been proposed to reduce the number of parameters, yielding lightweight models.
Ranked #3 on Age Estimation on FGNET
1 code implementation • 3 Apr 2019 • Xun Xu, Loong-Fah Cheong, Zhuwen Li
Subspace clustering has been extensively studied from the hypothesis-and-test, algebraic, and spectral clustering based perspectives.
no code implementations • 6 Mar 2019 • Kaimo Lin, Nianjuan Jiang, Loong Fah Cheong, Jiangbo Lu, Xun Xu
In this paper, we propose an efficient local-to-global method to identify background, based on the assumption that as long as there is sufficient camera motion, the cumulative background features will have the largest amount of trajectories.
no code implementations • 29 Jan 2019 • Xun Xu, Loong-Fah Cheong, Zhuwen Li
Multi-model fitting has been extensively studied from the random sampling and clustering perspectives.
no code implementations • 8 May 2018 • Chao Zhang, Ce Zhu, Jimin Xiao, Xun Xu, Yipeng Liu
Finally we demonstrate the effectiveness of both approaches by visualizing the Class Activation Map (CAM) and discover that grid dropout is more aware of the whole facial areas and more robust than neuron dropout for small training dataset.
1 code implementation • CVPR 2018 • Xun Xu, Loong-Fah Cheong, Zhuwen Li
Many real-world sequences cannot be conveniently categorized as general or degenerate; in such cases, imposing a false dichotomy in using the fundamental matrix or homography model for motion segmentation would lead to difficulty.
Ranked #1 on Motion Segmentation on KT3DMoSeg
1 code implementation • 21 Nov 2017 • Jiang Du, Xuemei Xie, Chenye Wang, Guangming Shi, Xun Xu, Yu-Xiang Wang
Recently, deep learning methods have made a significant improvement in compressive sensing image reconstruction task.
no code implementations • 26 Nov 2016 • Xun Xu, Timothy M. Hospedales, Shaogang Gong
In this work, we improve the ability of ZSL to generalise across this domain shift in both model- and data-centric ways by formulating a visual-semantic mapping with better generalisation properties and a dynamic data re-weighting method to prioritise auxiliary data that are relevant to the target classes.
Ranked #7 on Zero-Shot Action Recognition on Olympics
no code implementations • 15 Apr 2016 • Miao Sun, Tony X. Han, Xun Xu, Ming-Chang Liu, Ahmad Khodayari-Rostamabad
Deep Convolutional Neural Networks (CNN) have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene label- ing, due to their large learning capacity and resistance to overfit.
no code implementations • 13 Nov 2015 • Xun Xu, Timothy Hospedales, Shaogang Gong
This is a more challenging problem than existing ZSL of still images and/or attributes, because the mapping between video spacetime features of actions and the semantic space is more complex and harder to learn for the purpose of generalising over any cross-category domain shift.
no code implementations • 27 Jul 2015 • Xun Xu, Timothy Hospedales, Shaogang Gong
The growing rate of public space CCTV installations has generated a need for automated methods for exploiting video surveillance data including scene understanding, query, behaviour annotation and summarization.
no code implementations • 5 Feb 2015 • Xun Xu, Timothy Hospedales, Shaogang Gong
In this framework a mapping is constructed between visual features and a human interpretable semantic description of each category, allowing categories to be recognised in the absence of any training data.
Ranked #31 on Zero-Shot Action Recognition on UCF101