Picture for Renrui Zhang

Renrui Zhang

Personalize Segment Anything Model with One Shot

May 04, 2023
Renrui Zhang, Zhengkai Jiang, Ziyu Guo, Shilin Yan, Junting Pan, Hao Dong, Peng Gao, Hongsheng Li

Figure 1 for Personalize Segment Anything Model with One Shot

Figure 2 for Personalize Segment Anything Model with One Shot

Figure 3 for Personalize Segment Anything Model with One Shot

Figure 4 for Personalize Segment Anything Model with One Shot

* Code is available at https://github.com/ZrrSkywalker/Personalize-SAM

Access Paper or Ask Questions

LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

Apr 28, 2023
Peng Gao, Jiaming Han, Renrui Zhang, Ziyi Lin, Shijie Geng, Aojun Zhou, Wei Zhang, Pan Lu, Conghui He, Xiangyu Yue, Hongsheng Li, Yu Qiao

Figure 1 for LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

Figure 2 for LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

Figure 3 for LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

Figure 4 for LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

* Code and models are available at https://github.com/ZrrSkywalker/LLaMA-Adapter

Access Paper or Ask Questions

LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Mar 28, 2023
Renrui Zhang, Jiaming Han, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, Peng Gao, Yu Qiao

Figure 1 for LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Figure 2 for LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Figure 3 for LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Figure 4 for LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

* Work in Progress. Code is available at https://github.com/ZrrSkywalker/LLaMA-Adapter

Access Paper or Ask Questions

Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis

Mar 14, 2023
Renrui Zhang, Liuhui Wang, Yali Wang, Peng Gao, Hongsheng Li, Jianbo Shi

Figure 1 for Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis

Figure 2 for Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis

Figure 3 for Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis

Figure 4 for Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis

* Accepted by CVPR 2023. Code is available at https://github.com/ZrrSkywalker/Point-NN

Access Paper or Ask Questions

PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

Mar 14, 2023
Anthony Chen, Kevin Zhang, Renrui Zhang, Zihan Wang, Yuheng Lu, Yandong Guo, Shanghang Zhang

Figure 1 for PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

Figure 2 for PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

Figure 3 for PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

Figure 4 for PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

* Accepted by CVPR2023. Code is available at https://github.com/BLVLab/PiMAE

Access Paper or Ask Questions

Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking

Mar 09, 2023
Peng Gao, Renrui Zhang, Rongyao Fang, Ziyi Lin, Hongyang Li, Hongsheng Li, Qiao Yu

Figure 1 for Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking

Figure 2 for Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking

Figure 3 for Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking

Figure 4 for Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking

* 12 pages, 3 figures

Access Paper or Ask Questions