Emergent semantic segmentation: training-free dense-label-free extraction from vision-language models

• 主要作者: Luo, Jiayun
• 其他作者: Li Boyang
• 格式: Thesis-Master by Research
• 語言: English
• 出版: Nanyang Technological University 2024
• 主題: Computer and Information Science; Vision-language model; Open-vocabulary semantic segementation
• 在線閱讀: https://hdl.handle.net/10356/175765
• 機構: Nanyang Technological University

From an enormous amount of image-text pairs, large-scale vision-language models (VLMs) learn to implicitly associate image regions with words, which is vital for tasks such as image captioning and visual question answering. However, leveraging such pre-trained models for open-vocabulary semantic s...