no code implementations • 25 Mar 2024 • Ziyou Liang, Run Wang, Weifeng Liu, Yuyang Zhang, Wenyuan Yang, Lina Wang, Xingkai Wang
Unfortunately, the artifact patterns in fake images synthesized by different generative models are inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake.
no code implementations • 21 Mar 2024 • Changtong Zan, Liang Ding, Li Shen, Yibing Zhen, Weifeng Liu, DaCheng Tao
In this work, we design a two-stage fine-tuning algorithm to improve the instruction-following ability (especially the translation direction) of LLMs.
no code implementations • 5 Mar 2024 • Zhonghai Wang, Jie Jiang, Yibing Zhan, Bohao Zhou, Yanhong Li, Chong Zhang, Liang Ding, Hua Jin, Jun Peng, Xu Lin, Weifeng Liu
3) We introduce a standardized benchmark for evaluating medical LLM in Anesthesiology.
no code implementations • 5 Feb 2024 • Xiaoxing Wang, Jiaxing Li, Chao Xue, Wei Liu, Weifeng Liu, Xiaokang Yang, Junchi Yan, DaCheng Tao
BayesianOptimization(BO) is a sample-efficient black-box optimizer, and extensive methods have been proposed to build the absolute function response of the black-box function through a probabilistic surrogate model, including Tree-structured Parzen Estimator (TPE), random forest (SMAC), and Gaussian process (GP).
1 code implementation • 28 Jan 2024 • Weifeng Liu, Tianyi She, Jiawei Liu, Run Wang, Dongyu Yao, Ziyou Liang
In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, whereas these methods also pose potential and severe security threats to humanity.
1 code implementation • 28 Sep 2023 • Changtong Zan, Liang Ding, Li Shen, Yibin Lei, Yibing Zhan, Weifeng Liu, DaCheng Tao
Zero-shot translation (ZST), which is generally based on a multilingual neural machine translation model, aims to translate between unseen language pairs in training data.
1 code implementation • 20 Apr 2023 • Chiaming Hsu, Changtong Zan, Liang Ding, Longyue Wang, Xiaoting Wang, Weifeng Liu, Fu Lin, Wenbin Hu
Experiments on WMT17-EnZh XRE also show the effectiveness of our Prompt-XRE against other competitive baselines.
no code implementations • 24 Sep 2022 • Haojie Xu, Weifeng Liu, Jingwei Liu, Mingzheng Li, Yu Feng, Yasi Peng, Yunwei Shi, Xiao Sun, Meng Wang
Our experiments demonstrate the effectiveness of our proposed model and hybrid fusion strategy on multimodal fusion, and the AUC of our proposed model on the test set is 0. 8972.
1 code implementation • 20 Sep 2022 • Changtong Zan, Keqin Peng, Liang Ding, Baopu Qiu, Boan Liu, Shwai He, Qingyu Lu, Zheng Zhang, Chuang Liu, Weifeng Liu, Yibing Zhan, DaCheng Tao
As for model sizes, we scale the Transformer-Big up to the extremely large model that owns nearly 4. 7 Billion parameters, to fully enhance the model capacity for our Vega-MT.
Ranked #1 on Machine Translation on WMT 2022 English-Russian
1 code implementation • COLING 2022 • Changtong Zan, Liang Ding, Li Shen, Yu Cao, Weifeng Liu, DaCheng Tao
Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT).
1 code implementation • 16 Apr 2022 • Changtong Zan, Liang Ding, Li Shen, Yu Cao, Weifeng Liu, DaCheng Tao
For multilingual sequence-to-sequence pretrained language models (multilingual Seq2Seq PLMs), e. g. mBART, the self-supervised pretraining task is trained on a wide range of monolingual languages, e. g. 25 languages from CommonCrawl, while the downstream cross-lingual tasks generally progress on a bilingual language subset, e. g. English-German, making there exists the data discrepancy, namely domain discrepancy, and cross-lingual learning objective discrepancy, namely task discrepancy, between the pretraining and finetuning stages.
no code implementations • 1 Apr 2022 • Renjie Xu, Xinghao Yang, BaoDi Liu, Kai Zhang, Weifeng Liu
Few-Shot classification aims at solving problems that only a few samples are available in the training process.
no code implementations • 15 Mar 2022 • Rui Xu, Lei Xing, Shuai Shao, Lifei Zhao, BaoDi Liu, Weifeng Liu, Yicong Zhou
First, we propose a novel label prediction method, Isolated Graph Learning (IGL).
1 code implementation • 8 Mar 2022 • Jun Rao, Fei Wang, Liang Ding, Shuhan Qi, Yibing Zhan, Weifeng Liu, DaCheng Tao
In contrast to previous works, we focus on the reproducibility of the approaches and the examination of the elements that lead to improved performance by pretrained and nonpretrained models in retrieving images and text.
no code implementations • 16 Feb 2022 • Zhichen Ni, Honglong Chen, Zhe Li, Xiaomeng Wang, Na Yan, Weifeng Liu, Feng Xia
The vehicles can offload the computation intensive tasks to the cloud to save the resource of edge.
no code implementations • 1 Dec 2021 • Shuai Shao, Lei Xing, Rui Xu, Weifeng Liu, Yan-Jiang Wang, Bao-Di Liu
Inspired by this assumption, we propose a novel method Multi-Decision Fusing Model (MDFM), which comprehensively considers the decisions based on multiple FEMs to enhance the efficacy and robustness of the model.
no code implementations • 29 Sep 2021 • Xueqi Ma, Yubo Zhang, Weifeng Liu, Yue Gao
Based on the frequency principle on GNNs, we present a novel powerful GNNs framework, Multi-Scale Frequency Enhanced Graph Neural Networks (MSF-GNNs) which considers multi-scale representations from wavelet decomposition.
2 code implementations • 23 Aug 2021 • Xinghao Yang, Weifeng Liu, James Bailey, DaCheng Tao, Wei Liu
In this paper, we propose a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) method to examine the vulnerability of deep models.
1 code implementation • 22 Apr 2021 • Jian Pang, Dacheng Zhang, Huafeng Li, Weifeng Liu, Zhengtao Yu
This paper proposes a novel Interference Suppression Model (ISM) to deal with the interference caused by the hazy weather in domain adaptation person Re-ID.
1 code implementation • 3 Feb 2021 • Yibing Liu, Yangyang Guo, Jianhua Yin, Xuemeng Song, Weifeng Liu, Liqiang Nie
However, recent studies have pointed out that the highlighted image regions from the visual attention are often irrelevant to the given question and answer, leading to model confusion for correct visual reasoning.
no code implementations • 23 Oct 2020 • Shuai Shao, Rui Xu, Yan-Jiang Wang, Weifeng Liu, Bao-Di Liu
In this paper, we propose a hypergraph based sparse attention mechanism to tackle this issue and embed it into dictionary learning.
2 code implementations • 9 Oct 2020 • Xinghao Yang, Weifeng Liu, Shengli Zhang, Wei Liu, DaCheng Tao
To alleviate these problems, this paper proposes the targeted attention attack (TAA) method for real world road sign attack.
no code implementations • 21 Aug 2020 • Jinfeng Li, Weifeng Liu, Yicong Zhou, Jun Yu, Dapeng Tao
Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain.
no code implementations • 10 Apr 2020 • Xin Xu, Lei Liu, Weifeng Liu, Meng Wang, Ruimin Hu
To alleviate such a problem, we present an active hard sample mining framework via training an effective re-ID model with the least labeling efforts.
no code implementations • 23 Apr 2019 • Weifeng Liu, DaCheng Tao
One representative work in SSL is Laplacian regularization (LR), which smoothes the conditional distribution for classification along the manifold encoded in the graph Laplacian, however, it has been observed that LR biases the classification function towards a constant function which possibly results in poor generalization.
1 code implementation • 7 Mar 2019 • Shuai Shao, Yan-Jiang Wang, Bao-Di Liu, Weifeng Liu, Rui Xu
Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification.
no code implementations • 21 Jun 2018 • Xueqi Ma, Weifeng Liu, Dapeng Tao, Yicong Zhou
Therefore, we develop an ensemble p-Laplacian regularization (EpLapR) to fully approximate the intrinsic manifold of the data distribution.
no code implementations • 21 Jun 2018 • Xueqi Ma, Weifeng Liu, Shuying Li, Yicong Zhou
Graph based SSL and manifold regularization based SSL including Laplacian regularization (LapR) and Hypergraph Laplacian regularization (HLapR) are representative SSL methods and have achieved prominent performance by exploiting the relationship of sample distribution.
no code implementations • 7 Aug 2016 • Yanan Guo, Lei LI, Weifeng Liu, Jun Cheng, Dapeng Tao
Since human actions can be characterized by multiple feature representations extracted from Kinect and inertial sensors, multiview features must be encoded into a unified space optimal for human action recognition.
no code implementations • 6 Mar 2014 • Hongli Liu, Weifeng Liu, Yan-Jiang Wang
Different methods of classification based on sparse representation and Gabor kernels have been widely applied in the fields of facial analysis.
no code implementations • 15 Jul 2013 • Weifeng Liu, DaCheng Tao, Jun Cheng, Yuanyan Tang
In particular, mHDSC exploits Hessian regularization to steer the solution which varies smoothly along geodesics in the manifold, and treats the label information as an additional view of feature for incorporating the discriminative power for image annotation.
no code implementations • 4 May 2013 • Hui Li, Xiaomeng Wang, Weifeng Liu, Yan-Jiang Wang
Image enhancement is an important image processing technique that processes images suitably for a specific application e. g. image editing.