Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914973944381440 |
|---|---|
| author | Deng, Jieren Zhang, Haojian Ding, Kun Hu, Jianhua Zhang, Xingxuan Wang, Yunkuan |
| author_facet | Deng, Jieren Zhang, Haojian Ding, Kun Hu, Jianhua Zhang, Xingxuan Wang, Yunkuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01680 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection Deng, Jieren Zhang, Haojian Ding, Kun Hu, Jianhua Zhang, Xingxuan Wang, Yunkuan Computer Vision and Pattern Recognition 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. |
| title | Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01680 |