no code implementations • 22 May 2024 • Liyu Chen, Huaao Tang, Yi Wen, Hanting Chen, Wei Li, Junchao Liu, Jie Hu
To address these issues, we propose the Collaboration of Teachers Framework (CTF), which consists of multiple pairs of teacher and student models for training.
no code implementations • 7 May 2024 • Yuman Wang, Shuli Chen, Jie Hu, Da Zhou
In response to this challenge, we present two computational approaches grounded in stochastic cell population models: the first-order moment method (FOM) and the second-order moment method (SOM).
1 code implementation • 4 May 2024 • Yuchuan Tian, Zhijun Tu, Hanting Chen, Jie Hu, Chao Xu, Yunhe Wang
Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation.
1 code implementation • 30 Apr 2024 • Jie Hu, Yawen Huang, Yilin Lu, Guoyang Xie, Guannan Jiang, Yefeng Zheng, Zhichao Lu
The AnomalyXFusion framework comprises two distinct yet synergistic modules: the Multi-modal In-Fusion (MIF) module and the Dynamic Dif-Fusion (DDF) module.
no code implementations • 17 Apr 2024 • Yongdong Luo, Haojia Lin, Xiawu Zheng, Yigeng Jiang, Fei Chao, Jie Hu, Guannan Jiang, Songan Zhang, Rongrong Ji
3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships.
no code implementations • 9 Apr 2024 • Junbo Qiao, Wei Li, Haizhen Xie, Hanting Chen, Yunshuai Zhou, Zhijun Tu, Jie Hu, Shaohui Lin
Extensive experiments on multiple image processing tasks (e. g., image super-resolution (SR), JPEG artifact reduction, and image denoising) demonstrate the superiority of LIPT on both latency and PSNR.
no code implementations • 3 Apr 2024 • Simiao Li, Yun Zhang, Wei Li, Hanting Chen, Wenjia Wang, BingYi Jing, Shaohui Lin, Jie Hu
Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model.
no code implementations • 31 Mar 2024 • Zhijun Tu, Kunpeng Du, Hanting Chen, Hailing Wang, Wei Li, Jie Hu, Yunhe Wang
Recent advances have demonstrated the powerful capability of transformer architecture in image restoration.
no code implementations • 25 Mar 2024 • Quan Zhang, Xiaoyu Liu, Wei Li, Hanting Chen, Junchao Liu, Jie Hu, Zhiwei Xiong, Chun Yuan, Yunhe Wang
SPD leverages a self-distillation manner to distill the fused semantic priors to boost the performance of original IR models.
no code implementations • 7 Mar 2024 • Yu Zhu, Chuxiong Sun, Wenfei Yang, Wenqiang Wei, Bo Tang, Tianzhu Zhang, Zhiyu Li, Shifeng Zhang, Feiyu Xiong, Jie Hu, MingChuan Yang
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values.
no code implementations • 3 Mar 2024 • Huijie Guo, Ying Ba, Jie Hu, Lingyu Si, Wenwen Qiang, Lei Shi
Specifically, we update our proposed model through a bi-level optimization mechanism, enabling it to capture comprehensive features.
no code implementations • 18 Jan 2024 • Jie Hu, Vishwaraj Doshi, Do Young Eun
We study a family of distributed stochastic optimization algorithms where gradients are sampled by a token traversing a network of agents in random-walk fashion.
no code implementations • 17 Jan 2024 • Jie Hu, Vishwaraj Doshi, Do Young Eun
Two-timescale stochastic approximation (TTSA) is among the most general frameworks for iterative stochastic algorithms.
1 code implementation • 16 Dec 2023 • Qirui Ji, Jiangmeng Li, Jie Hu, Rui Wang, Changwen Zheng, Fanjiang Xu
To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature.
no code implementations • 13 Dec 2023 • Xin Ding, Xiaoyu Liu, Zhijun Tu, Yun Zhang, Wei Li, Jie Hu, Hanting Chen, Yehui Tang, Zhiwei Xiong, Baoqun Yin, Yunhe Wang
Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.
1 code implementation • 12 Dec 2023 • Mingjian Zhu, Hanting Chen, Mouxiao Huang, Wei Li, Hailin Hu, Jie Hu, Yunhe Wang
The misuse of AI imagery can have harmful societal effects, prompting the creation of detectors to combat issues like the spread of fake news.
no code implementations • 15 Nov 2023 • Cheng Luo, Jie Hu, Luping Xiang, Kun Yang, Kai-Kit Wong
Intelligent Reflecting Surface (IRS) utilizes low-cost, passive reflecting elements to enhance the passive beam gain, improve Wireless Energy Transfer (WET) efficiency, and enable its deployment for numerous Internet of Things (IoT) devices.
no code implementations • 10 Nov 2023 • Jiacheng Wei, Guosheng Lin, Henghui Ding, Jie Hu, Kim-Hui Yap
Point cloud datasets often suffer from inadequate sample sizes in comparison to image datasets, making data augmentation challenging.
1 code implementation • 26 Oct 2023 • Jiabin Tang, Lianghao Xia, Jie Hu, Chao Huang
Although recent STGNN models with contrastive learning aim to address these challenges, most of them use pre-defined augmentation strategies that heavily depend on manual design and cannot be customized for different Spatio-Temporal Graph (STG) scenarios.
no code implementations • 21 Oct 2023 • Luping Xiang, Ke Xu, Jie Hu, Christos Masouros, Kun Yang
This paper proposes a novel non-orthogonal multiple access (NOMA)-assisted orthogonal time-frequency space (OTFS)-integrated sensing and communication (ISAC) network, which uses unmanned aerial vehicles (UAVs) as air base stations to support multiple users.
no code implementations • 21 Oct 2023 • Luping Xiang, Ke Xu, Jie Hu, Kun Yang
In this paper, we propose a green beamforming design for the integrated sensing and communication (ISAC) system, using beam-matching error to assess radar performance.
no code implementations • 26 Sep 2023 • Hailing Wang, Wei Li, Yuanyuan Xi, Jie Hu, Hanting Chen, Longyu Li, Yunhe Wang
By matching similar patches between frames, objects with large motion ranges in dynamic scenes can be aligned, which can effectively alleviate the generation of artifacts.
1 code implementation • 25 Sep 2023 • Yun Zhang, Wei Li, Simiao Li, Hanting Chen, Zhijun Tu, Wenjia Wang, BingYi Jing, Shaohui Lin, Jie Hu
Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to compact student models.
Ranked #22 on Image Super-Resolution on Urban100 - 4x upscaling
no code implementations • 23 Sep 2023 • Xiaofan Li, Bo Peng, Jie Hu, Changyou Ma, DaiPeng Yang, Zhuyang Xie
Rather than risk potential pseudo-labeling errors or learning confusion by forcefully classifying these regions, we consider them as uncertainty regions, exempting them from pseudo-labeling and allowing the network to self-learn.
1 code implementation • ICCV 2023 • Jie Hu, Chen Chen, Liujuan Cao, Shengchuan Zhang, Annan Shu, Guannan Jiang, Rongrong Ji
Through extensive experiments conducted on the COCO and Cityscapes datasets, we demonstrate that PAIS is a promising framework for semi-supervised instance segmentation, particularly in cases where labeled data is severely limited.
no code implementations • 31 Jul 2023 • Xinyao Liu, Shengdong Du, Fengmao Lv, Hongtao Xue, Jie Hu, Tianrui Li
In the era of big data, the issue of data quality has become increasingly prominent.
no code implementations • 21 Jul 2023 • Ying Lu, Pei Shi, Xiao-Han Wang, Jie Hu, Shi-Ju Ran
In this work, we uncover that the ``variational entanglement-enhancing'' field (VEEF) robustly induces a persistent ballistic spreading of entanglement in quantum spin chains.
no code implementations • 11 Jun 2023 • Jie Hu, Qian Zhang, Heng Yin
Large language models (LLM) pre-trained with an enormous amount of natural language corpus have proved to be effective for understanding the implicit format syntax and generating format-conforming inputs.
no code implementations • 8 May 2023 • Vishwaraj Doshi, Jie Hu, Do Young Eun
We consider random walks on discrete state spaces, such as general undirected graphs, where the random walkers are designed to approximate a target quantity over the network topology via sampling and neighborhood exploration in the form of Markov chain Monte Carlo (MCMC) procedures.
2 code implementations • CVPR 2023 • Jie Hu, Linyan Huang, Tianhe Ren, Shengchuan Zhang, Rongrong Ji, Liujuan Cao
To reduce the computational overhead, we design a feature pyramid aggregator for the feature map extraction, and a separable dynamic decoder for the panoptic kernel generation.
no code implementations • 13 Mar 2023 • Jie Hu, Mengze Zeng, Enhua Wu
To bridge this gap, we collect and improve existing quantization methods and propose a gold guideline for post-training quantization.
1 code implementation • 9 Mar 2023 • Xingzhe Su, Wenwen Qiang, Jie Hu, Fengge Wu, Changwen Zheng, Fuchun Sun
Based on this SCM, we theoretically prove that the quality of generated images is positively correlated with the amount of feature information.
1 code implementation • CVPR 2023 • Suhang Ye, Yingyi Zhang, Jie Hu, Liujuan Cao, Shengchuan Zhang, Lei Shen, Jun Wang, Shouhong Ding, Rongrong Ji
Specifically, DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling Encoder (TDE) and Simulated Heatmaps.
no code implementations • 3 Feb 2023 • Jie Hu, Ke Xu, Luping Xiang, Kun Yang
Integrated data and energy transfer (IDET) is an advanced technology for enabling energy sustainability for massively deployed low-power electronic consumption components.
1 code implementation • CVPR 2023 • Dengsheng Chen, Jie Hu, Vince Junkai Tan, Xiaoming Wei, Enhua Wu
Federated learning enables the privacy-preserving training of neural network models using real-world data across distributed clients.
no code implementations • ICCV 2023 • Xiaoqiang Zhou, Huaibo Huang, Ran He, Zilei Wang, Jie Hu, Tieniu Tan
In particular, self-attention with cross-scale matching and convolution filters with different kernel sizes are designed to exploit the multi-scale features in images.
2 code implementations • CVPR 2023 • Zhijun Tu, Jie Hu, Hanting Chen, Yunhe Wang
In this paper, we study post-training quantization(PTQ) for image super resolution using only a few unlabeled calibration images.
1 code implementation • CVPR 2023 • Xudong Huang, Wei Li, Jie Hu, Hanting Chen, Yunhe Wang
We present Reference-guided Super-Resolution Neural Radiance Field (RefSR-NeRF) that extends NeRF to super resolution and photorealistic novel view synthesis.
no code implementations • 15 Dec 2022 • Junbo Qiao, Shaohui Lin, Yunlun Zhang, Wei Li, Jie Hu, Gaoqi He, Changbo Wang, Lizhuang Ma
Real-world image super-resolution (RISR) has received increased focus for improving the quality of SR images under unknown complex degradation.
no code implementations • 8 Dec 2022 • Zhonglun Wang, Jie Hu, Kun Yang
In this article, we proposethe SISO-OFDM and MISO-OFDM based IDET systems, which are the counterparts of our optimal wideband waveforming strategy in [1].
no code implementations • 6 Nov 2022 • Jie Hu, Yongquan Jiang, Yang Yan, Houchen Zuo
Based on this, this manuscript proposes the use of XGBoost model to identify superconductors; the first application of deep forest model to predict the critical temperature of superconductors; the first application of deep forest to predict the band gap of materials; and application of a new sub-network model to predict the Fermi energy level of materials.
1 code implementation • 30 Sep 2022 • Dengsheng Chen, Jie Hu, Wenwen Qiang, Xiaoming Wei, Enhua Wu
In this work, we deep dive into the model's behaviors with skip connections which can be formulated as a learnable Markov chain.
no code implementations • 15 Sep 2022 • Vishwaraj Doshi, Jie Hu, Do Young Eun
We consider a system in which two viruses of the Susceptible-Infected-Susceptible (SIS) type compete over general, overlaid graphs.
no code implementations • 15 Sep 2022 • Jie Hu, Vishwaraj Doshi, Do Young Eun
We consider the stochastic gradient descent (SGD) algorithm driven by a general stochastic sequence, including i. i. d noise and random walk on an arbitrary graph, among others; and analyze it in the asymptotic sense.
no code implementations • 8 Aug 2022 • Xiao-Han Wang, Pei Shi, Bin Xi, Jie Hu, Shi-Ju Ran
In this work, we demonstrate the validity of the deep convolutional neural network (CNN) on reconstructing the lattice topology (i. e., spin connectivities) in the presence of strong thermal fluctuations and unbalanced data.
no code implementations • 11 Jun 2022 • Benhan Li, Shengdong Du, Tianrui Li, Jie Hu, Zhen Jia
Time-series forecasting plays an important role in many real-world scenarios, such as equipment life cycle forecasting, weather forecasting, and traffic flow forecasting.
1 code implementation • 17 Mar 2022 • Yuan Cao, Zhiqiao Gao, Jie Hu, MingChuan Yang, Jinpeng Chen
As a result, informative samples in the margin area can not be discovered and AL performance are damaged.
no code implementations • 25 Feb 2022 • Jiabin Tang, Tang Qian, Shijing Liu, Shengdong Du, Jie Hu, Tianrui Li
Accurate traffic forecasting, the foundation of intelligent transportation systems (ITS), has never been more significant than nowadays due to the prosperity of smart cities and urban computing.
no code implementations • 19 Dec 2021 • Jie Hu, Ziheng Wu, Vince Tan, Zhilin Lu, Mengze Zeng, Enhua Wu
For example, we raise the top-1 accuracy of binarized ResNet26 from 57. 9% to 64. 0%.
no code implementations • 15 Nov 2021 • Shuo Jiang, Serhad Sarica, Binyang Song, Jie Hu, Jianxi Luo
Patent data have long been used for engineering design research because of its large and expanding size, and widely varying massive amount of design information contained in patents.
no code implementations • 29 Sep 2021 • Yuheng Lu, Jinpeng Chen, Chuxiong Sun, Jie Hu
In this work, we propose a novel framework which follows the anchor-based idea and aims at conveying distance information implicitly along the MPNN message passing steps for encoding position information, node attributes, and graph structure in a more flexible way.
no code implementations • 29 Sep 2021 • Wenwen Qiang, Jiangmeng Li, Jie Hu, Bing Su, Changwen Zheng, Hui Xiong
In this paper, we give an analysis of the existing representation learning framework of unsupervised domain adaptation and show that the learned feature representations of the source domain samples are with discriminability, compressibility, and transferability.
no code implementations • 20 Sep 2021 • Houchen Zuo, Yongquan Jiang, Yan Yang, Jie Hu
The experimental results show that the machine learning can predict the material properties accurately.
1 code implementation • 19 Sep 2021 • Zerun Wang, Liuyu Xiang, Fan Yang, Jinzhao Qian, Jie Hu, Haidong Huang, Jungong Han, Yuchen Guo, Guiguang Ding
While recent deep deblurring algorithms have achieved remarkable progress, most existing methods focus on the global deblurring problem, where the image blur mostly arises from severe camera shake.
1 code implementation • 16 Sep 2021 • Dengsheng Chen, Vince Tan, Zhilin Lu, Jie Hu
Federated Learning alleviates these problems by decentralizing model training, thereby removing the need for data transfer and aggregation.
no code implementations • 6 Sep 2021 • Jiangmeng Li, Wenwen Qiang, Hang Gao, Bing Su, Farid Razzak, Jie Hu, Changwen Zheng, Hui Xiong
To this end, we rethink the existing multi-view learning paradigm from the information theoretical perspective and then propose a novel information theoretical framework for generalized multi-view learning.
1 code implementation • ICCV 2021 • Lei Zhu, Qi She, Duo Li, Yanye Lu, Xuejing Kang, Jie Hu, Changhu Wang
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks.
no code implementations • 27 Jun 2021 • Shuo Jiang, Jie Hu, Christopher L. Magee, Jianxi Luo
In large technology companies, the requirements for managing and organizing technical documents created by engineers and managers have increased dramatically in recent years, which has led to a higher demand for more scalable, accurate, and automated document classification.
no code implementations • 6 Jun 2021 • Rui Hong, Peng-Fei Zhou, Bin Xi, Jie Hu, An-Chun Ji, Shi-Ju Ran
The hybridizations of machine learning and quantum physics have caused essential impacts to the methodology in both fields.
no code implementations • 3 Jun 2021 • Shuo Jiang, Jie Hu, Kristin L. Wood, Jianxi Luo
Design-by-Analogy (DbA) is a design methodology wherein new solutions, opportunities or designs are generated in a target domain based on inspiration drawn from a source domain; it can benefit designers in mitigating design fixation and improving design ideation outcomes.
no code implementations • 9 May 2021 • Yuheng Lu, Jinpeng Chen, Chuxiong Sun, Jie Hu
We show that GIRs get outperformed results in position-aware scenarios, and performances on typical GNNs could be improved by fusing GIR embeddings.
1 code implementation • 3 May 2021 • Jie Hu, Liujuan Cao, Yao Lu, Shengchuan Zhang, Yan Wang, Ke Li, Feiyue Huang, Ling Shao, Rongrong Ji
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #21 on Instance Segmentation on COCO test-dev
1 code implementation • 19 Apr 2021 • Chuxiong Sun, Hongming Gu, Jie Hu
To further improve scalable models on semi-supervised learning tasks, we propose Self-Label-Enhance (SLE) framework combining self-training approach and label propagation in depth.
Ranked #4 on Node Property Prediction on ogbn-papers100M
1 code implementation • CVPR 2021 • Lei Zhu, Qi She, Bin Zhang, Yanye Lu, Zhilin Lu, Duo Li, Jie Hu
Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence.
13 code implementations • CVPR 2021 • Duo Li, Jie Hu, Changhu Wang, Xiangtai Li, Qi She, Lei Zhu, Tong Zhang, Qifeng Chen
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision.
Ranked #705 on Image Classification on ImageNet
1 code implementation • CVPR 2021 • Xinyang Li, Shengchuan Zhang, Jie Hu, Liujuan Cao, Xiaopeng Hong, Xudong Mao, Feiyue Huang, Yongjian Wu, Rongrong Ji
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks.
Disentanglement Multimodal Unsupervised Image-To-Image Translation +1
1 code implementation • 30 Dec 2020 • Chuxiong Sun, Jie Hu, Hongming Gu, Jinpeng Chen, MingChuan Yang
Until the date of submission (Aug 26, 2022), AGDNs achieve top-1 performance on the ogbn-arxiv, ogbn-proteins and ogbl-ddi datasets and top-3 performance on the ogbl-citation2 dataset.
Ranked #1 on Link Property Prediction on ogbl-citation2
no code implementations • 21 Jun 2020 • Changchang Zeng, Shaobo Li, Qin Li, Jie Hu, Jianjun Hu
Machine Reading Comprehension (MRC) is a challenging Natural Language Processing(NLP) research field with wide real-world applications.
no code implementations • 21 Apr 2020 • Jihua Zhu, Jie Hu, Huimin Lu, Badong Chen, Zhongyu Li
Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem.
1 code implementation • ICCV 2021 • Jie Hu, Liujuan Cao, Qixiang Ye, Tong Tong, Shengchuan Zhang, Ke Li, Feiyue Huang, Rongrong Ji, Ling Shao
Based on the experimental results, we present three new findings that provide fresh insights into the inner logic of DNNs.
no code implementations • 10 Mar 2020 • Shuo Jiang, Jianxi Luo, Guillermo Ruiz Pava, Jie Hu, Christopher L. Magee
This approach is also illustrated in a case study of robot arm design retrieval.
no code implementations • 28 Jan 2020 • Xiaoli Liu, Pan Hu, Zhi Mao, Po-Chih Kuo, Peiyao Li, Chao Liu, Jie Hu, Deyu Li, Desen Cao, Roger G. Mark, Leo Anthony Celi, Zhengbo Zhang, Feihu Zhou
This study aims to develop an interpretable and generalizable model for early mortality prediction in elderly patients with MODS.
1 code implementation • NeurIPS 2019 • Jie Hu, Rongrong Ji, Shengchuan Zhang, Xiaoshuai Sun, Qixiang Ye, Chia-Wen Lin, Qi Tian
Learning representations with diversified information remains as an open problem.
1 code implementation • 29 Apr 2019 • Xinyang Li, Jie Hu, Shengchuan Zhang, Xiaopeng Hong, Qixiang Ye, Chenglin Wu, Rongrong Ji
Especially, AGUIT benefits from two-fold: (1) It adopts a novel semi-supervised learning process by translating attributes of labeled data to unlabeled data, and then reconstructing the unlabeled data by a cycle consistency operation.
no code implementations • International Journal of Modern Physics C 2019 • Jinfang Sheng, Kai Wang, Zejun Sun, Jie Hu, Bin Wang and Aman Ullah
In recent years, community detection has gradually become a hot topic in the complex network data mining field.
no code implementations • 16 Apr 2019 • Quanquan Shao, Jie Hu
This paper focuses on a robotic picking tasks in cluttered scenario.
no code implementations • 16 Apr 2019 • Quanquan Shao, Jie Hu, Weiming Wang, Yi Fang, Wenhai Liu, Jin Qi, Jin Ma
This paper focuses on robotic picking tasks in cluttered scenario.
1 code implementation • CVPR 2019 • Jie Hu, Rongrong Ji, Hong Liu, Shengchuan Zhang, Cheng Deng, Qi Tian
In this paper, we make the first attempt towards visual feature translation to break through the barrier of using features across different visual search systems.
9 code implementations • NeurIPS 2018 • Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Andrea Vedaldi
We also propose a parametric gather-excite operator pair which yields further performance gains, relate it to the recently-introduced Squeeze-and-Excitation Networks, and analyse the effects of these changes to the CNN feature activation statistics.
no code implementations • 26 Sep 2017 • Jiang Lu, Jie Hu, Guannan Zhao, Fenghua Mei, Chang-Shui Zhang
Crop diseases are responsible for the major production reduction and economic losses in agricultural industry world- wide.
82 code implementations • CVPR 2018 • Jie Hu, Li Shen, Samuel Albanie, Gang Sun, Enhua Wu
Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2. 251%, surpassing the winning entry of 2016 by a relative improvement of ~25%.
Ranked #59 on Image Classification on CIFAR-10
no code implementations • 14 Nov 2016 • Chengzhe Yan, Jie Hu, Chang-Shui Zhang
In this paper, a novel neural network architecture is proposed attempting to rectify text images with mild assumptions.
no code implementations • CVPR 2016 • Wangjiang Zhu, Jie Hu, Gang Sun, Xudong Cao, Yu Qiao
Training with a large proportion of irrelevant volumes will hurt performance.