InterpIoU: Robust bounding box regression loss within an interpolation-based IoU framework

Bounding box regression (BBR) is central to object detection, where regression loss plays a key role in precise localization. Existing IoU-based losses often rely on handcrafted geometric penalties to provide gradients in non-overlapping cases and improve localization. However, these geometric penalties are inherently sensitive to box geometry, producing unstable gradients in extreme cases and a subtle misalignment with the IoU objective, which harms small objects detection and yields undesired converge behaviors such as bounding box enlargement. To address these limitations, we introduce InterpIoU, an interpolation-based IoU optimization framework that rethinks BBR beyond handcrafted penalties. By bridging predictions and ground truth with interpolated boxes, InterpIoU supplies meaningful gradients in non-overlapping cases while ensuring consistent alignment with the BBR objective. Crucially, our findings challenge the convention of using geometric penalties, demonstrating they are often unnecessary and suboptimal. Building on InterpIoU, we propose Dynamic InterpIoU, which adjusts interpolation coefficients based on IoU values, adapting to diverse object distributions. Experiments on COCO, VisDrone, and PASCAL VOC demonstrate that our methods consistently outperform state-of-the-art IoU-based losses across detection frameworks, including YOLOv8 and DINO, with notable improvements for small object detection. • InterpIoU: a pure IoU-driven loss leveraging an interpolation mechanism. • Avoids gradient vanishing and bounding box enlargement in training. • Dynamic InterpIoU adapts interpolation by IoU, boosting small object detection. • Gradient analysis and simulations reveal geometric penalties are suboptimal. • Outperforms previous IoU-based losses on COCO, VOC, VisDrone across various detectors.