1 code implementation • 7 May 2024 • Jiajun Liu, Wenjun Ke, Peng Wang, Ziyu Shang, Jinhua Gao, Guozheng Li, Ke Ji, Yanhe Liu
On the one hand, existing methods usually learn new triples in a random order, destroying the inner structure of new KGs.
no code implementations • 27 Apr 2024 • Guozheng Li, Zijie Xu, Ziyu Shang, Jiajun Liu, Ke Ji, Yikai Guo
However, existing DRE methods still suffer from two serious issues: (1) hard to capture long and sparse multi-turn information, and (2) struggle to extract golden relations based on partial dialogues, which motivates us to discover more effective methods that can alleviate the above issues.
no code implementations • 27 Apr 2024 • Guozheng Li, Peng Wang, Jiajun Liu, Yikai Guo, Ke Ji, Ziyu Shang, Zijie Xu
To this end, we introduce \textsc{Micre} (\textbf{M}eta \textbf{I}n-\textbf{C}ontext learning of LLMs for \textbf{R}elation \textbf{E}xtraction), a new meta-training framework for zero and few-shot RE where an LLM is tuned to do ICL on a diverse collection of RE datasets (i. e., learning to learn in context for RE).
no code implementations • 27 Apr 2024 • Guozheng Li, Peng Wang, Wenjun Ke, Yikai Guo, Ke Ji, Ziyu Shang, Jiajun Liu, Zijie Xu
On the one hand, retrieving good demonstrations is a non-trivial process in RE, which easily results in low relevance regarding entities and relations.
no code implementations • 30 Mar 2024 • Wen Sheng, Zhong Zheng, Jiajun Liu, Han Lu, Hanyuan Zhang, Zhengyong Jiang, Zhihong Zhang, Daoping Zhu
Concurrently, we utilized Dice coefficient as the metric for assessing the segmentation outcomes produced by YNetr, having advantage of capturing different frequency information.
no code implementations • 21 Feb 2024 • Guozheng Li, Wenjun Ke, Peng Wang, Zijie Xu, Ke Ji, Jiajun Liu, Ziyu Shang, Qiqing Luo
The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations.
no code implementations • 9 Jan 2024 • Jiajun Liu, Siyuan Wang, Guangming Zhu, Liang Zhang, Ning li, Eryang Gao
We explore the performance of the model, including using styles randomly sampled from a prior normal distribution to generate images with various free-hand sketching styles, disentangling the painters' styles from known free-hand sketches to generate images with specific styles, and generating images of unknown classes that are not in the training set.
1 code implementation • NeurIPS 2023 • Mengyu Wang, Henghui Ding, Jun Hao Liew, Jiajun Liu, Yao Zhao, Yunchao Wei
We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process.
1 code implementation • 6 Nov 2023 • Xuwei Xu, Sen Wang, Yudong Chen, Yanping Zheng, Zhewei Wei, Jiajun Liu
Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands.
Ranked #188 on Image Classification on <h2>oi</h2>
1 code implementation • 26 Oct 2023 • Yudong Chen, Sen Wang, Jiajun Liu, Xuwei Xu, Frank de Hoog, Brano Kusy, Zi Huang
Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance.
no code implementations • 9 Oct 2023 • Xuwei Xu, Sen Wang, Yudong Chen, Jiajun Liu
Inspired by the channel shuffle design in ShuffleNetV2 \cite{ma2018shufflenet}, our module expands the feature channels of a tiny ViT and partitions the channels into two groups: the \textit{Attended} and \textit{Idle} groups.
1 code implementation • 9 Oct 2023 • Xuwei Xu, Changlin Li, Yudong Chen, Xiaojun Chang, Jiajun Liu, Sen Wang
By allowing the idle tokens to be re-selected in the following layers, IdleViT mitigates the negative impact of improper pruning in the early stages.
no code implementations • 5 Oct 2023 • Jia Syuen Lim, Ziwei Wang, Jiajun Liu, Abdelwahed Khamis, Reza Arablouei, Robert Barlow, Ryan McAllister
Regulatory compliance auditing across diverse industrial domains requires heightened quality assurance and traceability.
1 code implementation • 22 Aug 2023 • Bingqing Zhang, Sen Wang, Yifan Liu, Brano Kusy, Xue Li, Jiajun Liu
The ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD Scheduler to eliminate the aggregation of frames that are easy to detect, thus accelerating the VOD process.
1 code implementation • ICCV 2023 • Shujie Zhang, Tianyue Zheng, Zhe Chen, Jingzhi Hu, Abdelwahed Khamis, Jiajun Liu, Jun Luo
To overcome the challenge in labeling RF imaging given its human incomprehensible nature, OCHID-Fi employs a cross-modality and cross-domain training process.
1 code implementation • ICCV 2023 • Quan Tang, BoWen Zhang, Jiajun Liu, Fagui Liu, Yifan Liu
Experiments suggest that the proposed DToP architecture reduces on average $20\% - 35\%$ of computational cost for current semantic segmentation methods based on plain vision transformers without accuracy degradation.
1 code implementation • 14 May 2023 • Yanping Zheng, Zhewei Wei, Jiajun Liu
The experimental results demonstrate that our algorithm achieves state-of-the-art performance in both kinds of dynamic graphs.
1 code implementation • ICCV 2023 • Kunyang Han, Yong liu, Jun Hao Liew, Henghui Ding, Yunchao Wei, Jiajun Liu, Yitong Wang, Yansong Tang, Yujiu Yang, Jiashi Feng, Yao Zhao
Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS).
Knowledge Distillation Open Vocabulary Semantic Segmentation +4
no code implementations • 31 Oct 2022 • Ziwei Wang, Reza Arablouei, Jiajun Liu, Paulo Borges, Greg Bishop-hurley, Nicholas Heaney
Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving.
1 code implementation • 27 Oct 2022 • Yudong Chen, Sen Wang, Jiajun Liu, Xuwei Xu, Frank de Hoog, Zi Huang
Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features.
no code implementations • 15 Aug 2022 • Guoping Zhao, Bingqing Zhang, Mingyu Zhang, Yaxian Li, Jiajun Liu, Ji-Rong Wen
It models a video with a lattice feature graph in which the nodes represent regions of different granularity, with weighted edges that represent the spatial and temporal links.
1 code implementation • 15 Aug 2022 • Yaxian Li, Bingqing Zhang, Guoping Zhao, Mingyu Zhang, Jiajun Liu, Ziwei Wang, JiRong Wen
After a survey for person-tracking system-induced privacy concerns, we propose a black-box adversarial attack method on state-of-the-art human detection models called InvisibiliTee.
no code implementations • 1 Aug 2022 • Yang Li, Jiajun Liu, Brano Kusy, Ross Marchant, Brendan Do, Torsten Merz, Joey Crosswell, Andy Steven, Lachlan Tychsen-Smith, David Ahmedt-Aristizabal, Jeremy Oorloff, Peyman Moghadam, Russ Babcock, Megha Malpani, Ard Oerlemans
Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are ongoing to manage COTS populations to ecologically sustainable levels.
1 code implementation • 24 Jun 2022 • Reza Arablouei, Ziwei Wang, Greg J. Bishop-Hurley, Jiajun Liu
However, the multimodal animal behavior classification algorithm based on posterior probability fusion is preferable to the one based on feature concatenation as it delivers better classification accuracy, has less computational and memory complexity, is more robust to sensor data failure, and enjoys better modularity.
no code implementations • 3 Jun 2022 • Yanping Zheng, Hanzhi Wang, Zhewei Wei, Jiajun Liu, Sibo Wang
With the development of numerous GNN variants, recent years have witnessed groundbreaking results in improving the scalability of GNNs to work on static graphs with millions of nodes.
no code implementations • 29 Nov 2021 • Jiajun Liu, Brano Kusy, Ross Marchant, Brendan Do, Torsten Merz, Joey Crosswell, Andy Steven, Nic Heaney, Karl Von Richter, Lachlan Tychsen-Smith, David Ahmedt-Aristizabal, Mohammad Ali Armin, Geoffrey Carlin, Russ Babcock, Peyman Moghadam, Daniel Smith, Tim Davis, Kemal El Moujahid, Martin Wicke, Megha Malpani
Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are underway in an attempt to manage COTS populations to ecologically sustainable levels.
1 code implementation • 4 Jan 2021 • Thejan Rajapakshe, Rajib Rana, Sara Khalifa, Björn W. Schuller, Jiajun Liu
In addition, extended learning period is a general challenge for deep RL which can impact the speed of learning for SER.
no code implementations • 12 Jul 2019 • Guoping Zhao, Mingyu Zhang, Jiajun Liu, Ji-Rong Wen
Such tendency indicates that the model indeed learned how to toy with both image retrieval systems and human eyes.
no code implementations • 8 Oct 2017 • Yanlei Yu, Zhiwu Lu, Jiajun Liu, Guoping Zhao, Ji-Rong Wen, Kai Zheng
We propose a novel network representations learning model framework called RUM (network Representation learning throUgh Multi-level structural information preservation).
no code implementations • 10 Jul 2017 • Lianli Gao, Jingkuan Song, Xingyi Liu, Junming Shao, Jiajun Liu, Jie Shao
Given the high dimensionality and the high complexity of multimedia data, it is important to investigate new machine learning algorithms to facilitate multimedia data analysis.
no code implementations • 18 Feb 2015 • Jiajun Liu, Kun Zhao, Brano Kusy, Ji-Rong Wen, Raja Jurdak
The prediction of periodical time-series remains challenging due to various types of data distortions and misalignments.