Search Results for author: Haoyu Ma

Found 18 papers, 7 papers with code

Sparsity Winning Twice: Better Robust Generalization from More Efficient Training

1 code implementation ICLR 2022 Tianlong Chen, Zhenyu Zhang, Pengjun Wang, Santosh Balachandra, Haoyu Ma, Zehao Wang, Zhangyang Wang

We introduce two alternatives for sparse adversarial training: (i) static sparsity, by leveraging recent results from the lottery ticket hypothesis to identify critical sparse subnetworks arising from the early training; (ii) dynamic sparsity, by allowing the sparse subnetwork to adaptively adjust its connectivity pattern (while sticking to the same sparsity ratio) throughout training.

VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer

no code implementations17 Jan 2022 Mengshu Sun, Haoyu Ma, Guoliang Kang, Yifan Jiang, Tianlong Chen, Xiaolong Ma, Zhangyang Wang, Yanzhi Wang

To the best of our knowledge, this is the first time quantization has been incorporated into ViT acceleration on FPGAs with the help of a fully automatic framework to guide the quantization strategy on the software side and the accelerator implementations on the hardware side given the target frame rate.

Frame Quantization

Over-the-Air Aggregation for Federated Learning: Waveform Superposition and Prototype Validation

no code implementations27 Oct 2021 Huayan Guo, Yifan Zhu, Haoyu Ma, Vincent K. N. Lau, Kaibin Huang, Xiaofan Li, Huabin Nong, Mingyu Zhou

In this paper, we develop an orthogonal-frequency-division-multiplexing (OFDM)-based over-the-air (OTA) aggregation solution for wireless federated learning (FL).

Federated Learning Frame

AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation

no code implementations20 Oct 2021 Xiangyi Yan, Hao Tang, Shanlin Sun, Haoyu Ma, Deying Kong, Xiaohui Xie

One has to either downsample the image or use cropped local patches to reduce GPU memory usage, which limits its performance.

Medical Image Segmentation Semantic Segmentation

TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation

1 code implementation18 Oct 2021 Haoyu Ma, Liangjian Chen, Deying Kong, Zhe Wang, Xingwei Liu, Hao Tang, Xiangyi Yan, Yusheng Xie, Shih-Yao Lin, Xiaohui Xie

The 3D position encoding guided by the epipolar field provides an efficient way of encoding correspondences between pixels of different views.

3D Human Pose Estimation 3D Pose Estimation

Stingy Teacher: Sparse Logits Suffice to Fail Knowledge Distillation

no code implementations29 Sep 2021 Haoyu Ma, Yifan Huang, Tianlong Chen, Hao Tang, Chenyu You, Zhangyang Wang, Xiaohui Xie

However, it is unclear why the distorted distribution of the logits is catastrophic to the student model.

Knowledge Distillation

SGE net: Video object detection with squeezed GRU and information entropy map

no code implementations14 Jun 2021 Rui Su, Wenjing Huang, Haoyu Ma, Xiaowei Song, Jinglu Hu

Compared with object detection of static images, video object detection is more challenging due to the motion of objects, while providing rich temporal information.

Video Object Detection

Undistillable: Making A Nasty Teacher That CANNOT teach students

1 code implementation ICLR 2021 Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang

Knowledge Distillation (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models.

Knowledge Distillation

Spending Your Winning Lottery Better After Drawing It

1 code implementation8 Jan 2021 Ajay Kumar Jaiswal, Haoyu Ma, Tianlong Chen, Ying Ding, Zhangyang Wang

In this paper, we demonstrate that it is unnecessary for spare retraining to strictly inherit those properties from the dense network.

Knowledge Distillation

SIA-GCN: A Spatial Information Aware Graph Neural Network with 2D Convolutions for Hand Pose Estimation

no code implementations25 Sep 2020 Deying Kong, Haoyu Ma, Xiaohui Xie

In this paper, we extend GNNs along two directions: a) allowing features at each node to be represented by 2D spatial confidence maps instead of 1D vectors; and b) proposing an efficient operation to integrate information from neighboring nodes through 2D convolutions with different learnable kernels at each edge.

Frame Hand Pose Estimation

Real-MFF: A Large Realistic Multi-focus Image Dataset with Ground Truth

no code implementations28 Mar 2020 Juncheng Zhang, Qingmin Liao, Shaojun Liu, Haoyu Ma, Wenming Yang, Jing-Hao Xue

In this letter, we introduce a large and realistic multi-focus dataset called Real-MFF, which contains 710 pairs of source images with corresponding ground truth images.

Rotation-invariant Mixed Graphical Model Network for 2D Hand Pose Estimation

no code implementations5 Feb 2020 Deying Kong, Haoyu Ma, Yifei Chen, Xiaohui Xie

In this paper, we propose a new architecture named Rotation-invariant Mixed Graphical Model Network (R-MGMN) to solve the problem of 2D hand pose estimation from a monocular RGB image.

Hand Pose Estimation

Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation

1 code implementation24 Jan 2020 Yifei Chen, Haoyu Ma, Deying Kong, Xiangyi Yan, Jianbao Wu, Wei Fan, Xiaohui Xie

We propose a novel Nonparametric Structure Regularization Machine (NSRM) for 2D hand pose estimation, adopting a cascade multi-task architecture to learn hand structure and keypoint representations jointly.

Hand Pose Estimation

An α-Matte Boundary Defocus Model Based Cascaded Network for Multi-focus Image Fusion

2 code implementations29 Oct 2019 Haoyu Ma, Qingmin Liao, Juncheng Zhang, Shaojun Liu, Jing-Hao Xue

Based on this {\alpha}-matte defocus model and the generated data, a cascaded boundary aware convolutional network termed MMF-Net is proposed and trained, aiming to achieve clearer fusion results around the FDB.

Adaptive Graphical Model Network for 2D Handpose Estimation

no code implementations18 Sep 2019 Deying Kong, Yifei Chen, Haoyu Ma, Xiangyi Yan, Xiaohui Xie

In this paper, we propose a new architecture called Adaptive Graphical Model Network (AGMN) to tackle the task of 2D hand pose estimation from a monocular RGB image.

Hand Pose Estimation

Boundary Aware Multi-Focus Image Fusion Using Deep Neural Network

no code implementations30 Mar 2019 Haoyu Ma, Juncheng Zhang, Shaojun Liu, Qingmin Liao

Since it is usually difficult to capture an all-in-focus image of a 3D scene directly, various multi-focus image fusion methods are employed to generate it from several images focusing at different depths.

Cannot find the paper you are looking for? You can Submit a new open access paper.