8 papers
Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models
Zhaoyang Li, Yanjun Li, Wangkai Li +2
Vision-Language Models (VLMs) are costly at inference time because they must process long sequences of visual tokens. Existing token pruning methods often degrade under high compre…
Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation
Wangkai Li, Zhaoyang Li, Yuwen Pan +3
Adverse weather conditions significantly degrade the performance of LiDAR point cloud semantic segmentation networks by introducing large distribution shifts. Existing augmentation…
DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation
Wangkai Li, Rui Sun, Zhaoyang Li +2
While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect network calibration quality, resu…
Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective
Wangkai Li, Rui Sun, Zhaoyang Li +1
Pseudo-label learning is widely used in semantic segmentation, particularly in label-scarce scenarios such as unsupervised domain adaptation (UDA) and semisupervised learning (SSL)…
Balanced Learning for Domain Adaptive Semantic Segmentation
Wangkai Li, Rui Sun, Bohao Liao +2
Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Despite the effectiveness of s…
Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation
Wangkai Li, Rui Sun, Huayu Mai +1
Semantic segmentation suffers from significant performance degradation when the trained network is applied to a different domain. To address this issue, unsupervised domain adaptat…