20 citations · 37 across the 9 of their papers we have counts for
4 papers · 1 filter
Self-attention on Multi-Shifted Windows for Scene Segmentation
Litao Yu, Zhibin Li, Jian Zhang +1
Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.…
Lightweight Vision Transformer with Cross Feature Attention
Youpeng Zhao, Huadong Tang, Yingying Jiang +2
Recent advances in vision transformers (ViTs) have achieved great performance in visual recognition tasks. Convolutional neural networks (CNNs) exploit spatial inductive bias to le…
Unsupervised Point Cloud Pre-Training via Contrasting and Clustering
Guofeng Mei, Xiaoshui Huang, Juan Liu +2
Annotating large-scale point clouds is highly time-consuming and often infeasible for many complex real-world tasks. Point cloud pre-training has therefore become a promising strat…
PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization
Zhihang Yuan, Chenhao Xue, Yiqi Chen +2
Quantization is one of the most effective methods to compress neural networks, which has achieved great success on convolutional neural networks (CNNs). Recently, vision transforme…