34 citations · 80 across the 11 of their papers we have counts for
5 papers · 1 filter
SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow
Xiangtai Li, Jiangning Zhang, Yibo Yang +4
In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feat…
EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm
Jiangning Zhang, Xiangtai Li, Yabiao Wang +4
Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) and derives that both…
Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation
Xiangtai Li, Shilin Xu, Yibo Yang +3
Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and part segmentation into one task. Previous work mainly utilizes separated approaches to handle thing, stuff,…
ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation
Robin Wang, Yibo Yang, Dacheng Tao
Point cloud classifiers with rotation robustness have been widely discussed in the 3D deep learning community. Most proposed methods either use rotation invariant descriptors as in…
Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
Yibo Yang, Shixiang Chen, Xiangtai Li +3
Modern deep neural networks for classification usually jointly learn a backbone for representation and a linear classifier to output the logit of each class. A recent study has sho…