no code implementations • ECCV 2020 • Tong Wang, Yousong Zhu, Chaoyang Zhao, Wei Zeng, Yao-Wei Wang, Jinqiao Wang, Ming Tang
Most of existing object detectors usually adopt a small training batch size ( ~16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure.
no code implementations • ECCV 2020 • Xin Wen, Biying Li, Haiyun Guo, Zhiwei Liu, Guosheng Hu, Ming Tang, Jinqiao Wang
Some existing methods adopt distribution learning to tackle this issue by exploiting the semantic correlation between age labels.
Ranked #6 on Age Estimation on MORPH album2 (Caucasian)
no code implementations • ECCV 2020 • Xiaomei Zhang, Yingying Chen, Bingke Zhu, Jinqiao Wang, Ming Tang
Although human parsing has made great progress, it still faces a challenge, i. e., how to extract the whole foreground from similar or cluttered scenes effectively.
no code implementations • 7 May 2024 • Siyu Chen, Zheli Liu, Weihao Li, Zihe Hu, Mingming Zhang, Sheng Cui, Ming Tang
By introducing the Fermat number transform into chromatic dispersion compensation and adaptive equalization, the computational complexity has been reduced by 68% compared with the con? ventional implementation.
no code implementations • 21 Apr 2024 • Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Hao Li, Ming Tang, Jinqiao Wang
Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories.
1 code implementation • 16 Apr 2024 • Enming Zhang, Bingke Zhu, Yingying Chen, Qinghai Miao, Ming Tang, Jinqiao Wang
This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tasks.
no code implementations • 13 Apr 2024 • Rongguang Ye, Ming Tang
Fairness in federated learning has emerged as a critical concern, aiming to develop an unbiased model for any special group (e. g., male or female) of sensitive features.
no code implementations • 2 Apr 2024 • Xinbao Qiao, Meng Zhang, Ming Tang, Ermin Wei
In this work, we propose a Hessian-free online unlearning method.
1 code implementation • 14 Mar 2024 • Yufei Zhan, Yousong Zhu, Hongyin Zhao, Fan Yang, Ming Tang, Jinqiao Wang
Large Vision Language Models have achieved fine-grained object perception, but the limitation of image resolution remains a significant obstacle to surpass the performance of task-specific experts in complex and dense scenarios.
no code implementations • 29 Feb 2024 • Guojing Ge, Qi Song, Guibo Zhu, Yuting Zhang, Jinglu Chen, Miao Xin, Ming Tang, Jinqiao Wang
Blind face restoration is a challenging task due to the unknown and complex degradation.
no code implementations • 23 Feb 2024 • Pengchao Han, Chao Huang, Geng Tian, Ming Tang, Xin Liu
We further extend the analysis to non-convex objectives and where some clients may be unavailable during training.
1 code implementation • 19 Dec 2023 • Yongqi An, Xu Zhao, Tao Yu, Ming Tang, Jinqiao Wang
Retraining-free is important for LLMs' pruning methods.
no code implementations • 16 Dec 2023 • Lyudong Jin, Ming Tang, Meng Zhang, Hao Wang
The uncertain edge load dynamics, the nature of the fractional objective, and hybrid continuous-discrete action space (due to the joint optimization) make this problem challenging and existing approaches not directly applicable.
no code implementations • 27 Nov 2023 • Zhiyang Chen, Yousong Zhu, Yufei Zhan, Zhaowen Li, Chaoyang Zhao, Jinqiao Wang, Ming Tang
Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally.
no code implementations • 27 Nov 2023 • Jinghan He, Haiyun Guo, Ming Tang, Jinqiao Wang
2) Are the existing three classes of continual learning methods still applicable to the continual instruction tuning of LMMs?
1 code implementation • 24 Nov 2023 • Yufei Zhan, Yousong Zhu, Zhiyang Chen, Fan Yang, Ming Tang, Jinqiao Wang
More importantly, we present $\textbf{Griffon}$, a purely LVLM-based baseline, which does not require the introduction of any special tokens, expert models, or additional detection modules.
no code implementations • 13 Oct 2023 • Yizhou Yan, Xinyu Tang, Chao Huang, Ming Tang
The presence of label noise can severely degrade the FL performance, and some existing studies have focused on algorithm design for label denoising.
no code implementations • 28 Sep 2023 • Jiashi Gao, Changwu Huang, Ming Tang, Shin Hwei Tan, Xin Yao, Xuetao Wei
Recent advances in federated learning (FL) enable collaborative training of machine learning (ML) models from large-scale and widely dispersed clients while protecting their privacy.
1 code implementation • 29 Aug 2023 • Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Ming Tang, Jinqiao Wang
Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks.
no code implementations • 25 Aug 2023 • Ting Jiang, Zheng Gao, Yizhao Chen, Zihe Hu, Ming Tang
To comprehensively assess optical fiber communication system conditions, it is essential to implement joint estimation of the following four critical impairments: nonlinear signal-to-noise ratio (SNRNL), optical signal-to-noise ratio (OSNR), chromatic dispersion (CD) and differential group delay (DGD).
no code implementations • 23 Aug 2023 • Chao Huang, Geng Tian, Ming Tang
SplitFed learning (SFL) is a recent distributed approach that alleviates computation workload at the client device by splitting the model at a cut layer into two parts, where clients only need to train part of the model.
no code implementations • 9 Aug 2023 • Zhongyao Luo, Zhao Ge, Hao Wu, Ming Tang
Utilizing optical fibers to detect and pinpoint vibrations, Distributed Optical Fiber Vibration Sensing (DVS) technology provides real-time monitoring and surveillance of wide-reaching areas.
1 code implementation • 5 Jul 2023 • Ning Yang, Junrui Wen, Meng Zhang, Ming Tang
In this study, we address this issue by formulating a multi-objective offloading problem for MEC with multiple edges to minimize expected long-term energy consumption and transmission delay while considering unknown preferences as parameters.
1 code implementation • 21 Jun 2023 • Xu Zhao, Wenchao Ding, Yongqi An, Yinglong Du, Tao Yu, Min Li, Ming Tang, Jinqiao Wang
In this paper, we propose a speed-up alternative method for this fundamental task with comparable performance.
Ranked #4 on Zero-Shot Instance Segmentation on LVIS v1.0 val
no code implementations • 10 Apr 2023 • Zhaowen Li, Xu Zhao, Peigeng Ding, Zongxin Gao, Yuting Yang, Ming Tang, Jinqiao Wang
In the high-frequency branch, a derivative-filter-like architecture is designed to extract the high-frequency information while a light extractor is employed in the low-frequency branch because the low-frequency information is usually redundant.
1 code implementation • CVPR 2023 • Yongqi An, Xu Zhao, Tao Yu, Haiyun Guo, Chaoyang Zhao, Ming Tang, Jinqiao Wang
However, previous unsupervised deep learning BGS algorithms perform poorly in sophisticated scenarios such as shadows or night lights, and they cannot detect objects outside the pre-defined categories.
no code implementations • 28 Feb 2023 • Zhaowen Li, Yousong Zhu, Zhiyang Chen, Wei Li, Chaoyang Zhao, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang
However, its high random mask ratio would result in two serious problems: 1) the data are not efficiently exploited, which brings inefficient pre-training (\eg, 1600 epochs for MAE $vs.$ 300 epochs for the supervised), and 2) the high uncertainty and inconsistency of the pre-trained model, \ie, the prediction of the same patch may be inconsistent under different mask rounds.
no code implementations • 29 Jan 2023 • Xiaomei Zhang, Xiangyu Zhu, Ming Tang, Zhen Lei
Human parsing is a key topic in image processing with many applications, such as surveillance analysis, human-robot interaction, person search, and clothing category classification, among many others.
no code implementations • 3 Oct 2022 • Ruomei Qi, Jiarong Li, Jin Lin, Yonghua Song, Jiepeng Wang, Qiangqiang Cui, Yiwei Qiu, Ming Tang, Jian Wang
This paper focuses on the design of the PID temperature controller for an alkaline electrolysis system to achieve fast and stable temperature control.
2 code implementations • 28 Sep 2022 • Zhiyang Chen, Yousong Zhu, Zhaowen Li, Fan Yang, Wei Li, Haixin Wang, Chaoyang Zhao, Liwei Wu, Rui Zhao, Jinqiao Wang, Ming Tang
Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks.
no code implementations • 31 Aug 2022 • Zhaowen Li, Xu Zhao, Chaoyang Zhao, Ming Tang, Jinqiao Wang
Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision.
no code implementations • 14 Jun 2022 • Tianyi Yan, Kuan Zhu, Haiyun Guo, Guibo Zhu, Ming Tang, Jinqiao Wang
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person re-identification (Re-ID).
no code implementations • CVPR 2022 • Zhaowen Li, Yousong Zhu, Fan Yang, Wei Li, Chaoyang Zhao, Yingying Chen, Zhiyang Chen, Jiahao Xie, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang
Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.
no code implementations • 14 Mar 2022 • Hao Wu, Ming Tang
Here, we propose and experimentally demonstrate an OTDR deconvolution neural network based on deep convolutional neural networks.
1 code implementation • 8 Mar 2022 • Kuan Zhu, Haiyun Guo, Tianyi Yan, Yousong Zhu, Jinqiao Wang, Ming Tang
PASS learns to match the output of the local views and global views on the same [PART].
no code implementations • 27 Feb 2022 • Ruomei Qi, Jiarong Li, Jin Lin, Yonghua Song, Jiepeng Wang, Qiangqiang Cui, Yiwei Qiu, Ming Tang, Jian Wang
A control-oriented thermal model is established in the form of a third-order time-delay process, which is used for simulation and controller design.
1 code implementation • 18 Jan 2022 • Nanfei Jiang, Xu Zhao, Chaoyang Zhao, Yongqi An, Ming Tang, Jinqiao Wang
MaskSparsity imposes the fine-grained sparse regularization on the specific filters selected by a pruning mask, rather than all the filters of the model.
no code implementations • CVPR 2022 • Tong Wang, Yousong Zhu, Yingying Chen, Chaoyang Zhao, Bin Yu, Jinqiao Wang, Ming Tang
The decision boundary between any two categories is the angular bisector of their weight vectors.
no code implementations • 24 Dec 2021 • Zhiwei Liu, Xiangyu Zhu, Lu Yang, Xiang Yan, Ming Tang, Zhen Lei, Guibo Zhu, Xuetao Feng, Yan Wang, Jinqiao Wang
In the second stage, we design a mesh refinement transformer (MRT) to respectively refine each coarse reconstruction result via a self-attention mechanism.
Ranked #64 on 3D Human Pose Estimation on 3DPW (MPJPE metric)
no code implementations • 9 Sep 2021 • Zhao Ge, Li Shen, Can Zhao, Hao Wu, Zhiyong Zhao, Ming Tang
We propose a convolutional neural network (CNN) to process the data of conventional Brillouin optical time domain analysis (BOTDA) sensors, which achieves unprecedented performance improvement that allows to directly retrieve higher spatial resolution (SR) from the sensing system that use long pump pulses.
1 code implementation • 30 Jul 2021 • Zhiyang Chen, Yousong Zhu, Chaoyang Zhao, Guosheng Hu, Wei Zeng, Jinqiao Wang, Ming Tang
To address this problem, we propose a new Deformable Patch (DePatch) module which learns to adaptively split the images into patches with different positions and scales in a data-driven way rather than using predefined fixed patches.
Ranked #17 on Semantic Segmentation on DensePASS
no code implementations • CVPR 2021 • Linyu Zheng, Ming Tang, Yingying Chen, Guibo Zhu, Jinqiao Wang, Hanqing Lu
Despite considerable similarities between multiple object tracking (MOT) and single object tracking (SOT) tasks, modern MOT methods have not benefited from the development of SOT ones to achieve satisfactory performance.
no code implementations • NeurIPS 2021 • Zhaowen Li, Zhiyang Chen, Fan Yang, Wei Li, Yousong Zhu, Chaoyang Zhao, Rui Deng, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang
More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks.
no code implementations • 2 Apr 2021 • Kuan Zhu, Haiyun Guo, Shiliang Zhang, YaoWei Wang, Gaopan Huang, Honglin Qiao, Jing Liu, Jinqiao Wang, Ming Tang
In this paper, we introduce an alignment scheme in Transformer architecture for the first time and propose the Auto-Aligned Transformer (AAformer) to automatically locate both the human parts and non-human ones at patch-level.
1 code implementation • CVPR 2021 • Tong Wang, Yousong Zhu, Chaoyang Zhao, Wei Zeng, Jinqiao Wang, Ming Tang
To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies.
no code implementations • 5 Jan 2021 • Qi Zeng, Ying Liu, Liming Pan, Ming Tang
Our work provides insights on the importance of nodes in the multiplex network and gives a feasible framework to investigate influential spreaders in the asymmetrically coevolving dynamics.
Physics and Society
no code implementations • ICCV 2021 • Bin Yu, Ming Tang, Linyu Zheng, Guibo Zhu, Jinqiao Wang, Hao Feng, Xuetao Feng, Hanqing Lu
End-to-end discriminative trackers improve the state of the art significantly, yet the improvement in robustness and efficiency is restricted by the conventional discriminative model, i. e., least-squares based regression.
1 code implementation • 14 Oct 2020 • Xiaoqing Liang, Xu Zhao, Chaoyang Zhao, Nanfei Jiang, Ming Tang, Jinqiao Wang
This method decouples the distillation task of face detection into two subtasks, i. e., the classification distillation subtask and the regression distillation subtask.
no code implementations • 15 Sep 2020 • Li Shen, Zhiyong Zhao, Can Zhao, Hao Wu, Chao Lu, Ming Tang
The frequency dependency of Brillouin gain temporal envelope is investigated by simulation, and its impact on the recovered results of deconvolution algorithm is thoroughly analyzed.
1 code implementation • ECCV 2020 • Kuan Zhu, Haiyun Guo, Zhiwei Liu, Ming Tang, Jinqiao Wang
In this paper, we propose the identity-guided human semantic parsing approach (ISP) to locate both the human body parts and personal belongings at pixel-level for aligned person re-ID only with person identity labels.
Ranked #40 on Person Re-Identification on DukeMTMC-reID
1 code implementation • 20 Apr 2020 • Fan Wang, Ming Tang
An important objective of designing lithium-ion rechargeable battery cells is to maximize their rate performance without compromising the energy density, which is mainly achieved through computationally expensive numerical simulations at present.
Materials Science Applied Physics
no code implementations • 20 Sep 2019 • Xinghua Zheng, Ming Tang, Hankz Hankui Zhuo, Kevin X. Wen
Bike Sharing Systems (BSSs) have been adopted in many major cities of the world due to traffic congestion and carbon emissions.
no code implementations • ECCV 2020 • Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu
After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking.
no code implementations • CVPR 2019 • Zhiwei Liu, Xiangyu Zhu, Guosheng Hu, Haiyun Guo, Ming Tang, Zhen Lei, Neil M. Robertson, Jinqiao Wang
Despite this, we notice that the semantic ambiguity greatly degrades the detection performance.
Ranked #1 on Face Alignment on 300W (NME_inter-pupil (%, Full) metric)
no code implementations • 17 Jun 2018 • Ming Tang, Linyu Zheng, Bin Yu, Jinqiao Wang
To achieve the fast training and detection, a set of cyclic bases is introduced to construct the filter.
no code implementations • CVPR 2018 • Ming Tang, Bin Yu, Fan Zhang, Jinqiao Wang
In this paper, we will introduce the MKL into KCF in a different way than MKCF.
no code implementations • 12 Apr 2018 • Shiguang Wang, Jian Cheng, Haijun Liu, Ming Tang
To take advantage of the body parts and context information for pedestrian detection, we propose the part and context network (PCN) in this work.
no code implementations • 25 Nov 2017 • Jinqiao Wang, Ming Tang, Linyu Zheng, Jiayi Feng
In recent years, two types of trackers, namely correlation filter based tracker (CF tracker) and structured output tracker (Struck), have exhibited the state-of-the-art performance.
1 code implementation • 26 Jul 2017 • Bingke Zhu, Yingying Chen, Jinqiao Wang, Si Liu, Bo Zhang, Ming Tang
Finally, an automatic portrait animation system based on fast deep matting is built on mobile devices, which does not need any interaction and can realize real-time matting with 15 fps.
no code implementations • 24 Jul 2017 • Xu Zhao, Yingying Chen, Ming Tang, Jinqiao Wang
In the first stage, a convolutional encoder-decoder sub-network is employed to reconstruct the background images and encode rich prior knowledge of background scenes.
no code implementations • ICCV 2015 • Ming Tang, Jiayi Feng
In this paper, we will derive a multi-kernel correlation filter (MKCF) based tracker which fully takes advantage of the invariance-discriminative power spectrums of various features to further improve the performance.