LiG-DETR: Local-in-Global Reassembly in Latent Space for Aerial Object Detection

LiG-DETR introduces a Global-Local Reassembly framework for aerial object detection that captures high‑fidelity local features before compression and integrates them into a unified end‑to‑end DETR decoder. The method uses a shared encoder to extract both global and locally magnified features, reassembles the local features according to their spatial positions, and employs Context‑Preserved Selective Reassembly and Density‑Aware Adaptive Query Allocation to reduce redundant computation. Experiments demonstrate significant improvements on small and medium objects while maintaining strong performance on large objects, with favorable accuracy–efficiency trade‑offs and better cross‑domain generalization.

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 Computer Vision.

• diffusion
• computer-vision