LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fu, Shenghao, Yang, Qize, Mo, Qijie, Yan, Junkai, Wei, Xihan, Meng, Jingke, Xie, Xiaohua, Zheng, Wei-Shi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913672909029376
author Fu, Shenghao
Yang, Qize
Mo, Qijie
Yan, Junkai
Wei, Xihan
Meng, Jingke
Xie, Xiaohua
Zheng, Wei-Shi
author_facet Fu, Shenghao
Yang, Qize
Mo, Qijie
Yan, Junkai
Wei, Xihan
Meng, Jingke
Xie, Xiaohua
Zheng, Wei-Shi
contents Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption generation loss. We take advantage of a large language model to generate both region-level short captions for each region of interest and image-level long captions for the whole image. Under the supervision of the large language model, the resulting detector, LLMDet, outperforms the baseline by a clear margin, enjoying superior open-vocabulary ability. Further, we show that the improved LLMDet can in turn build a stronger large multi-modal model, achieving mutual benefits. The code, model, and dataset is available at https://github.com/iSEE-Laboratory/LLMDet.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18954
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models
Fu, Shenghao
Yang, Qize
Mo, Qijie
Yan, Junkai
Wei, Xihan
Meng, Jingke
Xie, Xiaohua
Zheng, Wei-Shi
Computer Vision and Pattern Recognition
Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption generation loss. We take advantage of a large language model to generate both region-level short captions for each region of interest and image-level long captions for the whole image. Under the supervision of the large language model, the resulting detector, LLMDet, outperforms the baseline by a clear margin, enjoying superior open-vocabulary ability. Further, we show that the improved LLMDet can in turn build a stronger large multi-modal model, achieving mutual benefits. The code, model, and dataset is available at https://github.com/iSEE-Laboratory/LLMDet.
title LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.18954