Search Results for author: Zhaohui Wang

Found 9 papers, 4 papers with code

PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models

1 code implementation3 Apr 2024 Fanxu Meng, Zhaohui Wang, Muhan Zhang

PiSSA shares the same architecture as LoRA, but initializes the adaptor matrices $A$ and $B$ with the principal components of the original matrix $W$, and put the remaining components into a residual matrix $W^{res} \in \mathbb{R}^{m \times n}$ which is frozen during fine-tuning.

GSM8K Quantization

CoSSegGaussians: Compact and Swift Scene Segmenting 3D Gaussians with Dual Feature Fusion

no code implementations11 Jan 2024 Bin Dou, Tianyu Zhang, Yongjia Ma, Zhaohui Wang, Zejian yuan

We propose Compact and Swift Segmenting 3D Gaussians(CoSSegGaussians), a method for compact 3D-consistent scene segmentation at fast rendering speed with only RGB images input.

Panoptic Segmentation Scene Segmentation +2

Seeing through the Mask: Multi-task Generative Mask Decoupling Face Recognition

no code implementations20 Nov 2023 Zhaohui Wang, Sufang Zhang, Jianteng Peng, Xinyi Wang, Yandong Guo

Therefore, this paper proposes a Multi-task gEnerative mask dEcoupling face Recognition (MEER) network to jointly handle these two tasks, which can learn occlusionirrelevant and identity-related representation while achieving unmasked face synthesis.

Face Generation Face Recognition

Towards Privacy-Supporting Fall Detection via Deep Unsupervised RGB2Depth Adaptation

1 code implementation23 Aug 2023 Hejun Xiao, Kunyu Peng, Xiangsheng Huang, Alina Roitberg1, Hao Li, Zhaohui Wang, Rainer Stiefelhagen

In this paper, we introduce a privacy-supporting solution that makes the RGB-trained model applicable in depth domain and utilizes depth data at test time for fall detection.

Domain Adaptation

H-DenseFormer: An Efficient Hybrid Densely Connected Transformer for Multimodal Tumor Segmentation

1 code implementation4 Jul 2023 Jun Shi, Hongyu Kan, Shulan Ruan, Ziqi Zhu, Minfan Zhao, Liang Qiao, Zhaohui Wang, Hong An, Xudong Xue

In this paper, we propose a hybrid densely connected network for tumor segmentation, named H-DenseFormer, which combines the representational power of the Convolutional Neural Network (CNN) and the Transformer structures.

Tumor Segmentation

Online Changepoint Detection on a Budget

no code implementations11 Jan 2022 Zhaohui Wang, Xiao Lin, Abhinav Mishra, Ram Sriharsha

In this paper, we are interested in changepoint detection algorithms which operate in an online setting in the sense that both its storage requirements and worst-case computational complexity per observation are independent of the number of previous observations.

DARNet: Dual-Attention Residual Network for Automatic Diagnosis of COVID-19 via CT Images

1 code implementation14 May 2021 Jun Shi, Huite Yi, Shulan Ruan, Zhaohui Wang, Xiaoyu Hao, Hong An, Wei Wei

The ongoing global pandemic of Coronavirus Disease 2019 (COVID-19) poses a serious threat to public health and the economy.

Computed Tomography (CT)

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