Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection
Abstract
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 8.74 AP, respectively.Our code is available at https://github.com/JarintotionDin/ZiRaGroundingDINO.
Keywords
Cite
@article{arxiv.2403.01680,
title = {Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection},
author = {Jieren Deng and Haojian Zhang and Kun Ding and Jianhua Hu and Xingxuan Zhang and Yunkuan Wang},
journal= {arXiv preprint arXiv:2403.01680},
year = {2024}
}
Comments
This paper has been accepted by NeurIPS 2024