DiffMatch: Visual-Language Guidance Makes Better Semi-supervised Change Detector

arXiv:2405.04788v1 Announce Type: new
Abstract: Change Detection (CD) aims to identify pixels with semantic changes between images. However, annotating massive numbers of pixel-level images is labor-intensive and costly, especially for multi-temporal images, which require pixel-wise comparisons by human experts. Considering the excellent performance of visual language models (VLMs) for zero-shot, open-vocabulary, etc. with prompt-based reasoning, it is promising to utilize VLMs to make better CD under limited labeled data. In this paper, we propose a VLM guidance-based semi-supervised CD method, …

abstract arxiv change cs.cv detection etc experts guidance however human identify images labor language language models massive numbers performance pixel pixels semantic semi semi-supervised temporal type visual visual language models vlms wise zero-shot