Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation

The paper proposes a method called Restrict, Don't Retrain that enhances zero-shot aerial segmentation by using inference-time guidance from a vision‑language model (VLM). It combines a frozen foundation model that labels every pixel with two VLM queries: one to select relevant classes and another to locate small objects missed by the base model. Experiments on four aerial datasets show consistent performance gains at each stage where the base model is competent.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• computer-vision
• multimodal