1 code implementation • 15 Apr 2024 • Haoxing Chen, Yaohui Li, Zizheng Huang, Yan Hong, Zhuoer Xu, Zhangxuan Gu, Jun Lan, Huijia Zhu, Weiqiang Wang
Recent advancements in efficient transfer learning (ETL) have shown remarkable success in fine-tuning VLMs within the scenario of limited data, introducing only a few parameters to harness task-specific insights from VLMs.
no code implementations • 22 Mar 2024 • Dazhong Rong, Guoyao Yu, Shuheng Shen, Xinyi Fu, Peng Qian, Jianhai Chen, Qinming He, Xing Fu, Weiqiang Wang
To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data.
1 code implementation • 5 Mar 2024 • Zheng Li, Xiang Li, Xinyi Fu, Xin Zhang, Weiqiang Wang, Shuo Chen, Jian Yang
To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student.
Ranked #1 on Prompt Engineering on Oxford-IIIT Pet Dataset
no code implementations • 28 Feb 2024 • Zhuoer Xu, Jianping Zhang, Shiwen Cui, Changhua Meng, Weiqiang Wang
Not only are these methods labor-intensive and require large budget costs, but the controllability of test prompt generation is lacking for the specific testing domain of LLM applications.
no code implementations • 6 Feb 2024 • Ruofan Wu, Guanhua Fang, Qiying Pan, Mingyang Zhang, Tengfei Liu, Weiqiang Wang, Wenbiao Zhao
Graph representation learning (GRL) is critical for extracting insights from complex network structures, but it also raises security concerns due to potential privacy vulnerabilities in these representations.
no code implementations • 28 Nov 2023 • Jintang Li, Jiawang Dan, Ruofan Wu, Jing Zhou, Sheng Tian, Yunfei Liu, Baokun Wang, Changhua Meng, Weiqiang Wang, Yuchang Zhu, Liang Chen, Zibin Zheng
Over the past few years, graph neural networks (GNNs) have become powerful and practical tools for learning on (static) graph-structure data.
1 code implementation • 21 Nov 2023 • Haoxing Chen, Yaohui Li, Yan Hong, Zizheng Huang, Zhuoer Xu, Zhangxuan Gu, Jun Lan, Huijia Zhu, Weiqiang Wang
Recent methods mainly focus on learning multi-modal features aligned with class names to enhance the generalization ability to unseen categories.
Ranked #1 on GZSL Video Classification on ActivityNet-GZSL (cls)
no code implementations • 31 Oct 2023 • Ruofan Wu, Mingyang Zhang, Lingjuan Lyu, Xiaolong Xu, Xiuquan Hao, Xinyi Fu, Tengfei Liu, Tianyi Zhang, Weiqiang Wang
The paradigm of vertical federated learning (VFL), where institutions collaboratively train machine learning models via combining each other's local feature or label information, has achieved great success in applications to financial risk management (FRM).
no code implementations • 17 Oct 2023 • Jiawang Dan, Ruofan Wu, Yunpeng Liu, Baokun Wang, Changhua Meng, Tengfei Liu, Tianyi Zhang, Ningtao Wang, Xing Fu, Qi Li, Weiqiang Wang
Recently, the idea of designing neural models on graphs using the theory of graph kernels has emerged as a more transparent as well as sometimes more expressive alternative to MPNNs known as kernel graph neural networks (KGNNs).
no code implementations • 18 Sep 2023 • Qiying Pan, Ruofan Wu, Tengfei Liu, Tianyi Zhang, Yifei Zhu, Weiqiang Wang
Federated training of Graph Neural Networks (GNN) has become popular in recent years due to its ability to perform graph-related tasks under data isolation scenarios while preserving data privacy.
1 code implementation • 19 Aug 2023 • Bo Zhang, Yuxuan Duan, Jun Lan, Yan Hong, Huijia Zhu, Weiqiang Wang, Li Niu
To address these challenges, we propose a controllable image composition method that unifies four tasks in one diffusion model: image blending, image harmonization, view synthesis, and generative composition.
no code implementations • 17 Aug 2023 • Liyue Chen, Linian Wang, Jinyu Xu, Shuai Chen, Weiqiang Wang, Wenbiao Zhao, Qiyu Li, Leye Wang
For example, consider cross-domain fraud detection, where there are two types of transactions: credit and non-credit.
no code implementations • 17 Aug 2023 • Xinting Liao, Chaochao Chen, Weiming Liu, Pengyang Zhou, Huabin Zhu, Shuheng Shen, Weiqiang Wang, Mengling Hu, Yanchao Tan, Xiaolin Zheng
In server, GNE reaches an agreement among inconsistent and discrepant model deviations from clients to server, which encourages the global model to update in the direction of global optimum without breaking down the clients optimization toward their local optimums.
no code implementations • ICCV 2023 • Zhuoer Xu, Zhangxuan Gu, Jianping Zhang, Shiwen Cui, Changhua Meng, Weiqiang Wang
Transfer-based attackers craft adversarial examples against surrogate models and transfer them to victim models deployed in the black-box situation.
no code implementations • 27 Jul 2023 • Guiqin Zhao, Lianlei Shan, Weiqiang Wang
Deep networks have demonstrated significant success in detecting changes in bi-temporal remote sensing images and have found applications in various fields.
1 code implementation • 11 Jun 2023 • Qiang Lyu, Weiqiang Wang
We empirically demonstrate that the learned component prototypes have good class transferability and can be reused to construct compositional prototypes for novel classes.
1 code implementation • NeurIPS 2023 • Haoxing Chen, Zhuoer Xu, Zhangxuan Gu, Jun Lan, Xing Zheng, Yaohui Li, Changhua Meng, Huijia Zhu, Weiqiang Wang
Specifically, we build our model on a diffusion model and carefully modify the network structure to enable the model for drawing multilingual characters with the help of glyph and position information.
1 code implementation • CVPR 2023 • Zhangxuan Gu, Zhuoer Xu, Haoxing Chen, Jun Lan, Changhua Meng, Weiqiang Wang
Recent object detection approaches rely on pretrained vision-language models for image-text alignment.
1 code implementation • 5 May 2023 • Yuzhong Zhao, Weijia Wu, Zhuang Li, Jiahong Li, Weiqiang Wang
This paper introduces a novel video text synthesis technique called FlowText, which utilizes optical flow estimation to synthesize a large amount of text video data at a low cost for training robust video text spotters.
no code implementations • 6 Apr 2023 • Yuke Hu, Wei Liang, Ruofan Wu, Kai Xiao, Weiqiang Wang, Xiaochen Li, Jinfei Liu, Zhan Qin
Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks.
no code implementations • 6 Mar 2023 • Jiafu Wu, Mufeng Yao, Dong Wu, Mingmin Chi, Baokun Wang, Ruofan Wu, Xin Fu, Changhua Meng, Weiqiang Wang
Graph representation plays an important role in the field of financial risk control, where the relationship among users can be constructed in a graph manner.
no code implementations • 4 Feb 2023 • Ruofan Wu, Boqun Ma, Hong Jin, Wenlong Zhao, Weiqiang Wang, Tianyi Zhang
The application of graph representation learning techniques to the area of financial risk management (FRM) has attracted significant attention recently.
no code implementations • 27 Jan 2023 • Xiaolong Xu, Lingjuan Lyu, Yihong Dong, Yicheng Lu, Weiqiang Wang, Hong Jin
With the frequent happening of privacy leakage and the enactment of privacy laws across different countries, data owners are reluctant to directly share their raw data and labels with any other party.
2 code implementations • 6 Dec 2022 • Zhangxuan Gu, Haoxing Chen, Zhuoer Xu, Jun Lan, Changhua Meng, Weiqiang Wang
Extensive experimental results on COCO and LVIS show that DiffusionInst achieves competitive performance compared to existing instance segmentation models with various backbones, such as ResNet and Swin Transformers.
Ranked #8 on Instance Segmentation on LVIS v1.0 val
1 code implementation • 16 Nov 2022 • Haoxing Chen, Zhangxuan Gu, Yaohui Li, Jun Lan, Changhua Meng, Weiqiang Wang, Huaxiong Li
The MGD effectively applies distinct convolution to the foreground and background, learning the representations of foreground and background regions as well as their correlations to the global harmonization, facilitating local visual consistency for the images much more efficiently.
Ranked #2 on Image Harmonization on HAdobe5k(1024$\times$1024)
1 code implementation • 7 Oct 2022 • Zhuoer Xu, Guanghui Zhu, Changhua Meng, Shiwen Cui, ZhenZhe Ying, Weiqiang Wang, Ming Gu, Yihua Huang
In this paper, we propose an efficient automated attacker called A2 to boost AT by generating the optimal perturbations on-the-fly during training.
no code implementations • 27 Sep 2022 • Weiqiang Wang, Xuefei Zhe, Qiuhong Ke, Di Kang, Tingguang Li, Ruizhi Chen, Linchao Bao
Along with the novel system, we also present a new dataset dedicated to the multi-action motion synthesis task, which contains both action tags and their contextual information.
no code implementations • 24 Aug 2022 • Weixi Zhao, Weiqiang Wang
We propose a novel attention-based 2D-to-3D pose estimation network for graph-structured data, named KOG-Transformer, and a 3D pose-to-shape estimation network for hand data, named GASE-Net.
no code implementations • 4 Jul 2022 • Yuzhong Zhao, Yuanqiang Cai, Weijia Wu, Weiqiang Wang
Generally pre-training and long-time training computation are necessary for obtaining a good-performance text detector based on deep networks.
2 code implementations • 20 May 2022 • Jintang Li, Ruofan Wu, Wangbin Sun, Liang Chen, Sheng Tian, Liang Zhu, Changhua Meng, Zibin Zheng, Weiqiang Wang
The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding.
1 code implementation • 20 Apr 2022 • Jintang Li, Jie Liao, Ruofan Wu, Liang Chen, Zibin Zheng, Jiawang Dan, Changhua Meng, Weiqiang Wang
To mitigate such a threat, considerable research efforts have been devoted to increasing the robustness of GCNs against adversarial attacks.
1 code implementation • CVPR 2022 • Zhangxuan Gu, Changhua Meng, Ke Wang, Jun Lan, Weiqiang Wang, Ming Gu, Liqing Zhang
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings.
document understanding Optical Character Recognition (OCR) +1
1 code implementation • 17 Jan 2022 • ZhenZhe Ying, Zhuoer Xu, Zhifeng Li, Weiqiang Wang, Changhua Meng
Despite the success of deep learning in computer vision and natural language processing, Gradient Boosted Decision Tree (GBDT) is yet one of the most powerful tools for applications with tabular data such as e-commerce and FinTech.
no code implementations • CVPR 2022 • Weixi Zhao, Weiqiang Wang, Yunjie Tian
In 2D-to-3D pose estimation, it is important to exploit the spatial constraints of 2D joints, but it is not yet well modeled.
1 code implementation • 17 Sep 2021 • Weixi Zhao, Yunjie Tian, Qixiang Ye, Jianbin Jiao, Weiqiang Wang
Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation.
no code implementations • ICLR 2022 • Zhiyuan Zhang, Lingjuan Lyu, Weiqiang Wang, Lichao Sun, Xu sun
In this work, we observe an interesting phenomenon that the variations of parameters are always AWPs when tuning the trained clean model to inject backdoors.
no code implementations • 3 Jul 2021 • Hui Li, Xing Fu, Ruofan Wu, Jinyu Xu, Kai Xiao, xiaofu Chang, Weiqiang Wang, Shuai Chen, Leilei Shi, Tao Xiong, Yuan Qi
Deep learning provides a promising way to extract effective representations from raw data in an end-to-end fashion and has proven its effectiveness in various domains such as computer vision, natural language processing, etc.
no code implementations • 22 Jun 2021 • Xiang Ni, Xiaolong Xu, Lingjuan Lyu, Changhua Meng, Weiqiang Wang
Recently, Graph Neural Network (GNN) has achieved remarkable success in various real-world problems on graph data.
no code implementations • 19 Nov 2020 • Yuanqiang Cai, Chang Liu, Weiqiang Wang, Qixiang Ye
With only bounding-box annotations in the spatial domain, existing video scene text detection (VSTD) benchmarks lack temporal relation of text instances among video frames, which hinders the development of video text-related applications.
no code implementations • 20 Apr 2020 • Ji Gan, Weiqiang Wang, Ke Lu
Chinese is one of the most widely used languages in the world, yet online handwritten Chinese character recognition (OLHCCR) remains challenging.
no code implementations • 19 Apr 2020 • Chao Qu, Hui Li, Chang Liu, Junwu Xiong, James Zhang, Wei Chu, Weiqiang Wang, Yuan Qi, Le Song
We propose a \emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \emph{joint} policy through the interactions over agents.
Multi-agent Reinforcement Learning reinforcement-learning +2
1 code implementation • 18 Mar 2020 • Yuan-Qiang Cai, Longyin Wen, Libo Zhang, Dawei Du, Weiqiang Wang
In this paper, we propose a new task, ie, simultaneously object localization and counting, abbreviated as Locount, which requires algorithms to localize groups of objects of interest with the number of instances.
no code implementations • 25 Sep 2019 • Yuan-Qiang Cai, Dawei Du, Libo Zhang, Longyin Wen, Weiqiang Wang, Yanjun Wu, Siwei Lyu
Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background.
no code implementations • 25 Apr 2019 • XiaoBin Li, Weiqiang Wang
Loss functions play a key role in training superior deep neural networks.
2 code implementations • 24 Apr 2019 • Hongzhu Li, Weiqiang Wang
The outputs of a CTC-trained model tend to form a series of spikes separated by strongly predicted blanks, know as the spiky problem.
no code implementations • 10 Nov 2017 • Shao Huang, Weiqiang Wang, Shengfeng He, Rynson W. H. Lau
Egocentric videos, which mainly record the activities carried out by the users of the wearable cameras, have drawn much research attentions in recent years.
no code implementations • 8 Nov 2017 • Haiqing Ren, Weiqiang Wang
And the proposed Memory Pool Unit is proved to be a simple hidden layer function and obtains a competitive recognition results.