This paper presents Incremental Vision-Language Object Detection (IVLOD), a
novel learning task designed to incrementally adapt pre-trained Vision-Language
Object Detection Models (VLODMs) to various specialized domains, while
simultaneously preserving their zero-shot generalization capabilities for the
generalized domain. To address this new challenge, we present the
Zero-interference Reparameterizable Adaptation (ZiRa), a novel method that
introduces Zero-interference Loss and reparameterization techniques to tackle
IVLOD without incurring additional inference costs or a significant increase in
memory usage. Comprehensive experiments on COCO and ODinW-13 datasets
demonstrate that ZiRa effectively safeguards the zero-shot generalization
ability of VLODMs while continuously adapting to new tasks. Specifically, after
training on ODinW-13 datasets, ZiRa exhibits superior performance compared to
CL-DETR and iDETR, boosting zero-shot generalizability by substantial 13.91 and
8.71 AP, respectively.

本文提出了一种增量的视觉 - 语言物体检测（IVLOD）学习任务，旨在在保持泛化能力的同时，逐步调整预训练的视觉 - 语言物体检测模型（VLODMs）以适应不同的专用领域。为了解决这一新挑战，我们提出了一种称为 Zero-interference Reparameterizable Adaptation（ZiRa）的新方法，该方法引入了零干扰损失和参数重参数化技术来处理 IVLOD，而不会增加额外的推理成本或显著增加内存使用量。对 COCO 和 ODinW-13 数据集进行的综合实验表明，ZiRa 能够有效保护 VLODMs 的零泛化能力，并持续适应新任务。具体来说，在 ODinW-13 数据集上训练后，ZiRa 的性能优于 CL-DETR 和 iDETR，分别提高了 13.91 和 8.71 个 AP 的零泛化能力。