2 code implementations • 21 Mar 2024 • Xinyu Shi, Zecheng Hao, Zhaofei Yu
Based on DSSA, we propose a novel spiking Vision Transformer architecture called SpikingResformer, which combines the ResNet-based multi-stage architecture with our proposed DSSA to improve both performance and energy efficiency while reducing parameters.
no code implementations • 1 Feb 2024 • Zecheng Hao, Xinyu Shi, Zhiyu Pan, Yujia Liu, Zhaofei Yu, Tiejun Huang
Compared to traditional Artificial Neural Network (ANN), Spiking Neural Network (SNN) has garnered widespread academic interest for its intrinsic ability to transmit information in a more biological-inspired and energy-efficient manner.
1 code implementation • 18 Jul 2022 • Xinyu Shi, Dong Wei, Yu Zhang, Donghuan Lu, Munan Ning, Jiashun Chen, Kai Ma, Yefeng Zheng
A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images.
Ranked #4 on Few-Shot Semantic Segmentation on COCO-20i (1-shot)
1 code implementation • 7 Jul 2022 • Jiashun Chen, Donghuan Lu, Yu Zhang, Dong Wei, Munan Ning, Xinyu Shi, Zhe Xu, Yefeng Zheng
In this study, we propose a novel Deformer module along with a multi-scale framework for the deformable image registration task.
2 code implementations • 26 Feb 2022 • Chaofeng Chen, Xinyu Shi, Yipeng Qin, Xiaoming Li, Xiaoguang Han, Tao Yang, Shihui Guo
Unlike image-space methods, our FeMaSR restores HR images by matching distorted LR image {\it features} to their distortion-free HR counterparts in our pretrained HR priors, and decoding the matched features to obtain realistic HR images.