Songhe Deng — accepted AI-conference papers

2024

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

Weizhao He, Yang Zhang, Wei Zhuo, Linlin Shen, Jiaqi Yang, Songhe Deng +1

CVPR 2024poster

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains and their performances degrade significantly while applied to a disti…

Cited by 16 Source ↗PDF ↗Scholar ↗

2024

Tune-An-Ellipse: CLIP Has Potential to Find What You Want

Jinheng Xie, Songhe Deng, Bing Li, Haozhe Liu, Yawen Huang, Yefeng Zheng +4

CVPR 2024highlight

Visual prompting of large vision language models such as CLIP exhibits intriguing zero-shot capabilities. A manually drawn red circle commonly used for highlighting can guide CLIP's attention to the surrounding region to identify specific objects within an image. Without precise object proposals how…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗