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

• Main Author: Luo, Jiayun
• Other Authors: Li Boyang
• Format: Thesis-Master by Research
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Vision-language model; Open-vocabulary semantic segementation
• Online Access: https://hdl.handle.net/10356/175765
• Institution: 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...