Yunhe Wang* — accepted AI-conference papers

2024

Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation

Zhenliang Ni, Xinghao Chen*, Yingjie Zhai, Yehui Tang, Yunhe Wang*

ECCV 2024poster

"Semantic segmentation is an important task for numerous applications but it is still quite challenging to achieve advanced performance with limited computational costs. In this paper, we present CGRSeg, an efficient yet competitive segmentation framework based on context-guided spatial feature reco…

Cited by 25 Source ↗PDF ↗code ↗Scholar ↗

2024

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning

Shibo Jie, Yehui Tang, Jianyuan Guo, Zhi-Hong Deng*, Kai Han*, Yunhe Wang*

ECCV 2024poster

"Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, , pruning inattentive tokens or merging similar tokens. However, when applied to downstream tasks, these approaches suffer from significant performance drop when the…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗