no code implementations • 29 Mar 2024 • Yue Wang, Zhi Tian, FXin Fan, Zhipeng Cai, Cameron Nowzari, Kai Zeng
The rapid growth of Internet of Things (IoT) has led to the widespread deployment of smart IoT devices at wireless edge for collaborative machine learning tasks, ushering in a new era of edge learning.
no code implementations • 11 Mar 2024 • Hui Su, Zhi Tian, Xiaoyu Shen, Xunliang Cai
However, the original scaling law paper by OpenAI did not disclose the complete details necessary to derive the precise scaling law formulas, and their conclusions are only based on models containing up to 1. 5 billion parameters.
no code implementations • 2 Dec 2023 • Shuang Xu, Sifan Zhou, Zhi Tian, Jizhou Ma, Qiong Nie, Xiangxiang Chu
Current traditional methods for LiDAR-camera extrinsics estimation depend on offline targets and human efforts, while learning-based approaches resort to iterative refinement for calibration results, posing constraints on their generalization and application in on-board systems.
1 code implementation • 16 Jul 2023 • Xingrong Dong, Zhaoxian Wu, Qing Ling, Zhi Tian
But we prove that, even with a class of state-of-the-art robust aggregation rules, in an adversarial environment and in the presence of Byzantine participants, distributed online gradient descent can only achieve a linear adversarial regret bound, which is tight.
1 code implementation • 9 Jun 2023 • BoWen Zhang, Liyang Liu, Minh Hieu Phan, Zhi Tian, Chunhua Shen, Yifan Liu
This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework and introduces \textbf{SegViTv2}.
Ranked #16 on Semantic Segmentation on ADE20K
1 code implementation • 5 Feb 2023 • Sifan Zhou, Zhi Tian, Xiangxiang Chu, Xinyu Zhang, Bo Zhang, Xiaobo Lu, Chengjian Feng, Zequn Jie, Patrick Yin Chiang, Lin Ma
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios.
no code implementations • 17 Jan 2023 • Yu Zhang, Yue Wang, Zhi Tian, Geert Leus, Gong Zhang
This paper proposes a super-resolution harmonic retrieval method for uncorrelated strictly non-circular signals, whose covariance and pseudo-covariance present Toeplitz and Hankel structures, respectively.
no code implementations • 14 Nov 2022 • Liyang Lu, Wenbo Xu, Yue Wang, Zhi Tian
To this end, the minimum number of required measurements for successful recovery is first derived in terms of its probabilistic lower bound.
no code implementations • 14 Nov 2022 • Liyang Lu, Wenbo Xu, Yue Wang, Zhi Tian
In this paper, we propose a blind-block orthogonal least squares-based compressive spectrum sensing (B-BOLS-CSS) algorithm, which utilizes a novel blind stopping rule to cut the cords to these prior information.
no code implementations • 29 Oct 2022 • Guanqiang Zhou, Ping Xu, Yue Wang, Zhi Tian
In this paper, we propose a new algorithm that equips distributed learning with robustness measures against both distributional shifts and byzantine attacks.
no code implementations • 29 Oct 2022 • Yue Wang, Zhi Tian, Xin Fan, Yan Huo, Cameron Nowzari, Kai Zeng
With the proliferation of versatile Internet of Things (IoT) services, smart IoT devices are increasingly deployed at the edge of wireless networks to perform collaborative machine learning tasks using locally collected data, giving rise to the edge learning paradigm.
1 code implementation • 12 Oct 2022 • BoWen Zhang, Zhi Tian, Quan Tang, Xiangxiang Chu, Xiaolin Wei, Chunhua Shen, Yifan Liu
We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit.
Ranked #4 on Semantic Segmentation on COCO-Stuff test
no code implementations • 10 Aug 2022 • Xin Fan, Yue Wang, Yan Huo, Zhi Tian
data issues and Byzantine attacks, global data samples are introduced in CB-DSL and shared among IoT workers, which not only alleviates the local data heterogeneity effectively but also enables to fully utilize the exploration-exploitation mechanism of swarm intelligence.
no code implementations • 8 Aug 2022 • Hannan Lu, Zhi Tian, Lirong Yang, Haibing Ren, WangMeng Zuo
The compact instance stream effectively improves the segmentation accuracy of the unseen pixels, while fusing two streams with the adaptive routing map leads to an overall performance boost.
no code implementations • 4 Aug 2022 • Ping Xu, Yue Wang, Xiang Chen, Zhi Tian
We then propose a novel learning framework named Online Decentralized Kernel learning via Linearized ADMM (ODKLA) to efficiently solve the online decentralized kernel learning problem.
no code implementations • 27 May 2022 • Zhi Tian, Xiangxiang Chu, Xiaoming Wang, Xiaolin Wei, Chunhua Shen
In this work, we tackle this challenging issue with a novel range view projection mechanism, and for the first time demonstrate the benefits of fusing multi-frame point clouds for a range-view based detector.
no code implementations • 11 Apr 2022 • Liyang Lu, Wenbo Xu, Yue Wang, Zhi Tian
As an enabling technique of cognitive radio (CR), compressive spectrum sensing (CSS) based on compressive sensing (CS) can detect the spectrum opportunities from wide frequency bands efficiently and accurately by using sub-Nyquist sampling rate.
no code implementations • 7 Apr 2022 • Ali Mirzaeian, Zhi Tian, Sai Manoj P D, Banafsheh S. Latibari, Ioannis Savidis, Houman Homayoun, Avesta Sasan
We conceptualize the model parameters/features associated with each class as a mass characterized by its centroid location and the spread (standard deviation of the distance) of features around the centroid.
1 code implementation • 19 Jan 2022 • Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang, Anton Van Den Hengel
We propose a direct, regression-based approach to 2D human pose estimation from single images.
Ranked #2 on Keypoint Detection on MS COCO
no code implementations • 28 Nov 2021 • Fuxun Yu, Weishan Zhang, Zhuwei Qin, Zirui Xu, Di Wang, ChenChen Liu, Zhi Tian, Xiang Chen
Federated learning learns from scattered data by fusing collaborative models from local nodes.
1 code implementation • 24 Oct 2021 • Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen, Yanning Zhang
Neural Architecture Search (NAS) has shown great potential in effectively reducing manual effort in network design by automatically discovering optimal architectures.
no code implementations • 18 Oct 2021 • Xin Fan, Yue Wang, Yan Huo, Zhi Tian
As a promising distributed learning technology, analog aggregation based federated learning over the air (FLOA) provides high communication efficiency and privacy provisioning under the edge computing paradigm.
1 code implementation • NeurIPS 2021 • BoWen Zhang, Yifan Liu, Zhi Tian, Chunhua Shen
This neural representation enables our decoder to leverage the smoothness prior in the semantic label space, and thus makes our decoder more efficient.
3 code implementations • CVPR 2021 • Weian Mao, Zhi Tian, Xinlong Wang, Chunhua Shen
We propose a fully convolutional multi-person pose estimation framework using dynamic instance-aware convolutions, termed FCPose.
8 code implementations • NeurIPS 2021 • Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, Chunhua Shen
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.
Ranked #48 on Semantic Segmentation on ADE20K val
no code implementations • 8 Apr 2021 • Xin Fan, Yue Wang, Yan Huo, Zhi Tian
Federated learning (FL) is an attractive paradigm for making use of rich distributed data while protecting data privacy.
no code implementations • 30 Mar 2021 • Xin Fan, Yue Wang, Yan Huo, Zhi Tian
For distributed learning among collaborative users, this paper develops and analyzes a communication-efficient scheme for federated learning (FL) over the air, which incorporates 1-bit compressive sensing (CS) into analog aggregation transmissions.
no code implementations • 29 Mar 2021 • Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang
We propose a human pose estimation framework that solves the task in the regression-based fashion.
Ranked #26 on Pose Estimation on MPII Human Pose (using extra training data)
2 code implementations • 22 Feb 2021 • Xiangxiang Chu, Zhi Tian, Bo Zhang, Xinlong Wang, Chunhua Shen
Built on PEG, we present Conditional Position encoding Vision Transformer (CPVT).
no code implementations • 5 Feb 2021 • Zhi Tian, BoWen Zhang, Hao Chen, Chunhua Shen
In the literature, top-performing instance segmentation methods typically follow the paradigm of Mask R-CNN and rely on ROI operations (typically ROIAlign) to attend to each instance.
2 code implementations • CVPR 2021 • Zhi Tian, Chunhua Shen, Xinlong Wang, Hao Chen
We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training.
no code implementations • 19 Nov 2020 • Hao Chen, Chunhua Shen, Zhi Tian
To our knowledge, DR1Mask is the first panoptic segmentation framework that exploits a shared feature map for both instance and semantic segmentation by considering both efficacy and efficiency.
no code implementations • 18 Sep 2020 • William Barnhart, Zhi Tian
This scheme is of particular significance when there is only one accessible database -- a special case that turns out to be more challenging for PIR in the multi-database case.
no code implementations • 15 Aug 2020 • Fuxun Yu, Weishan Zhang, Zhuwei Qin, Zirui Xu, Di Wang, ChenChen Liu, Zhi Tian, Xiang Chen
Specifically, we design a feature-oriented regulation method ({$\Psi$-Net}) to ensure explicit feature information allocation in different neural network structures.
no code implementations • 30 Jul 2020 • Yanbo Wang, Zhi Tian
Estimation of third-order statistics relies on the availability of a huge amount of data records, which can pose severe challenges on the data collecting hardware in terms of considerable storage costs, overwhelming energy consumption, and unaffordably high sampling rate especially when dealing with high-dimensional data such as wideband signals.
no code implementations • 14 Jun 2020 • Zhi Tian, Chunhua Shen, Hao Chen, Tong He
In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications.
7 code implementations • CVPR 2020 • Rufeng Zhang, Zhi Tian, Chunhua Shen, Mingyu You, Youliang Yan
To date, instance segmentation is dominated by twostage methods, as pioneered by Mask R-CNN.
7 code implementations • ECCV 2020 • Zhi Tian, Chunhua Shen, Hao Chen
We propose a simple yet effective instance segmentation framework, termed CondInst (conditional convolutions for instance segmentation).
2 code implementations • 3 Feb 2020 • Wei Yin, Xinlong Wang, Chunhua Shen, Yifan Liu, Zhi Tian, Songcen Xu, Changming Sun, Dou Renyin
Compared with previous learning objectives, i. e., learning metric depth or relative depth, we propose to learn the affine-invariant depth using our diverse dataset to ensure both generalization and high-quality geometric shapes of scenes.
no code implementations • 28 Jan 2020 • Ping Xu, Yue Wang, Xiang Chen, Zhi Tian
This paper studies the decentralized optimization and learning problem where multiple interconnected agents aim to learn an optimal decision function defined over a reproducing kernel Hilbert space by jointly minimizing a global objective function, with access to their own locally observed dataset.
no code implementations • ECCV 2020 • Tong He, Dong Gong, Zhi Tian, Chunhua Shen
3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding.
Ranked #28 on 3D Instance Segmentation on ScanNet(v2)
9 code implementations • CVPR 2020 • Hao Chen, Kunyang Sun, Zhi Tian, Chunhua Shen, Yongming Huang, Youliang Yan
The proposed BlendMask can effectively predict dense per-pixel position-sensitive instance features with very few channels, and learn attention maps for each instance with merely one convolution layer, thus being fast in inference.
Ranked #13 on Real-time Instance Segmentation on MSCOCO
8 code implementations • 18 Nov 2019 • Zhi Tian, Hao Chen, Chunhua Shen
We propose the first direct end-to-end multi-person pose estimation framework, termed DirectPose.
Ranked #13 on Keypoint Detection on COCO test-dev
1 code implementation • ICCV 2019 • Linjie Xing, Zhi Tian, Weilin Huang, Matthew R. Scott
We evaluate CharNet on three standard benchmarks, where it consistently outperforms the state-of-the-art approaches [25, 24] by a large margin, e. g., with improvements of 65. 33%->71. 08% (with generic lexicon) on ICDAR 2015, and 54. 0%->69. 23% on Total-Text, on end-to-end text recognition.
Ranked #2 on Scene Text Detection on ICDAR 2015
no code implementations • 15 Sep 2019 • Weiyu Li, Yaohua Liu, Zhi Tian, Qing Ling
COLA is proven to be convergent when the local cost functions have Lipschitz continuous gradients and the censoring threshold is summable.
3 code implementations • CVPR 2020 • Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen, Yanning Zhang
The success of deep neural networks relies on significant architecture engineering.
Ranked #124 on Object Detection on COCO test-dev
86 code implementations • ICCV 2019 • Zhi Tian, Chunhua Shen, Hao Chen, Tong He
By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training.
Ranked #4 on Pedestrian Detection on TJU-Ped-campus
1 code implementation • CVPR 2019 • Tong He, Chunhua Shen, Zhi Tian, Dong Gong, Changming Sun, Youliang Yan
To tackle this dilemma, we propose a knowledge distillation method tailored for semantic segmentation to improve the performance of the compact FCNs with large overall stride.
no code implementations • CVPR 2019 • Zhi Tian, Tong He, Chunhua Shen, Youliang Yan
In this work, we propose a data-dependent upsampling (DUpsampling) to replace bilinear, which takes advantages of the redundancy in the label space of semantic segmentation and is able to recover the pixel-wise prediction from low-resolution outputs of CNNs.
Ranked #46 on Semantic Segmentation on PASCAL Context
2 code implementations • CVPR 2018 • Tong He, Zhi Tian, Weilin Huang, Chunhua Shen, Yu Qiao, Changming Sun
This allows the two tasks to work collaboratively by shar- ing convolutional features, which is critical to identify challenging text instances.
27 code implementations • 12 Sep 2016 • Zhi Tian, Weilin Huang, Tong He, Pan He, Yu Qiao
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image.