activity
20212023
most citedLLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

119 citations · 249 across the 18 of their papers we have counts for

collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV20231 cited

Less is More: Towards Efficient Few-shot 3D Semantic Segmentation via Training-free Networks

Xiangyang Zhu, Renrui Zhang, Bowei He +4

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot semantic segmentation methods first pre-train the m…

cs.CV2023

Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking

Peng Gao, Renrui Zhang, Rongyao Fang +4

Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decod…

cs.CV202313 cited

Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners

Renrui Zhang, Xiangfei Hu, Bohao Li +5

Visual recognition in low-data regimes requires deep neural networks to learn generalized representations from limited training samples. Recently, CLIP-based methods have shown pro…

cs.CV202334 cited

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

Renrui Zhang, Liuhui Wang, Ziyu Guo +4

We present a Non-parametric Network for 3D point cloud analysis, Point-NN, which consists of purely non-learnable components: farthest point sampling (FPS), k-nearest neighbors (k-…

cs.CV20223 cited

Recurrent Bilinear Optimization for Binary Neural Networks

Sheng Xu, Yanjing Li, Tiancheng Wang +6

Binary Neural Networks (BNNs) show great promise for real-world embedded devices. As one of the critical steps to achieve a powerful BNN, the scale factor calculation plays an esse…

cs.CV20224 cited

Collaboration of Pre-trained Models Makes Better Few-shot Learner

Renrui Zhang, Bohao Li, Wei Zhang +4

Few-shot classification requires deep neural networks to learn generalized representations only from limited training images, which is challenging but significant in low-data regim…