Search Results for author: Jiajun Liu

Found 31 papers, 14 papers with code

Towards Continual Knowledge Graph Embedding via Incremental Distillation

1 code implementation7 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.

Knowledge Graph Embedding

Empirical Analysis of Dialogue Relation Extraction with Large Language Models

no code implementations27 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.

Relation Relation Extraction

Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors

no code implementations27 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).

Few-Shot Learning In-Context Learning +2

Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction

no code implementations27 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.

In-Context Learning Language Modelling +4

YNetr: Dual-Encoder architecture on Plain Scan Liver Tumors (PSLT)

no code implementations30 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.


Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction

no code implementations21 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.

Blocking In-Context Learning +1

Content-Conditioned Generation of Stylized Free hand Sketches

no code implementations9 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.

Data Augmentation Image Generation

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

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.

Denoising Dichotomous Image Segmentation +4

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation

1 code implementation6 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.

Efficient ViTs

Understanding the Effects of Projectors in Knowledge Distillation

1 code implementation26 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.

Knowledge Distillation

No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling

1 code implementation9 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.

Plug n' Play: Channel Shuffle Module for Enhancing Tiny Vision Transformers

no code implementations9 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.

Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection

1 code implementation22 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.

Object object-detection +1

OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision

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.

3D Pose Estimation Hand Pose Estimation

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

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.

Image Classification Segmentation +1

Decoupled Graph Neural Networks for Large Dynamic Graphs

1 code implementation14 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.

Recommendation Systems

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

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

Improved Feature Distillation via Projector Ensemble

1 code implementation27 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.

Knowledge Distillation Multi-Task Learning

InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee

1 code implementation15 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.

Adversarial Attack Human Detection

STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval

no code implementations15 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.

Representation Learning Retrieval +1

A Real-time Edge-AI System for Reef Surveys

no code implementations1 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.

Computational Efficiency object-detection +1

Multimodal sensor data fusion for in-situ classification of animal behavior using accelerometry and GNSS data

1 code implementation24 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.


Instant Graph Neural Networks for Dynamic Graphs

no code implementations3 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.

The CSIRO Crown-of-Thorn Starfish Detection Dataset

no code implementations29 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.

BIG-bench Machine Learning Management

Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN

no code implementations12 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.

Image Classification Image Retrieval +1

RUM: network Representation learning throUgh Multi-level structural information preservation

no code implementations8 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).

Representation Learning

Learning in High-Dimensional Multimedia Data: The State of the Art

no code implementations10 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.

BIG-bench Machine Learning feature selection +3

Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets

no code implementations18 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.

Time Series Time Series Analysis

Cannot find the paper you are looking for? You can Submit a new open access paper.