Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation
A single consumer-grade GPU running a vision-language model (VLM) is used to supply missing guidance on pixel-level segmentation, improving segmentation while producing structured, auditable evidence that drives the result and can be inspected on its own.
Teresa DiMeola, Charles Walter, Hong Xiao
· 0 citations