RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Fangyi, Zhang, Han, Yang, Zhantao, Chen, Hao, Hu, Kai, Savvides, Marios
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916266022797312
author Chen, Fangyi
Zhang, Han
Yang, Zhantao
Chen, Hao
Hu, Kai
Savvides, Marios
author_facet Chen, Fangyi
Zhang, Han
Yang, Zhantao
Chen, Hao
Hu, Kai
Savvides, Marios
contents Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs. However, such data is limited in practice due to significant annotation costs. In this work, we propose RTGen to generate scalable open-vocabulary region-text pairs and demonstrate its capability to boost the performance of open-vocabulary object detection. RTGen includes both text-to-region and region-to-text generation processes on scalable image-caption data. The text-to-region generation is powered by image inpainting, directed by our proposed scene-aware inpainting guider for overall layout harmony. For region-to-text generation, we perform multiple region-level image captioning with various prompts and select the best matching text according to CLIP similarity. To facilitate detection training on region-text pairs, we also introduce a localization-aware region-text contrastive loss that learns object proposals tailored with different localization qualities. Extensive experiments demonstrate that our RTGen can serve as a scalable, semantically rich, and effective source for open-vocabulary object detection and continue to improve the model performance when more data is utilized, delivering superior performance compared to the existing state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19854
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection
Chen, Fangyi
Zhang, Han
Yang, Zhantao
Chen, Hao
Hu, Kai
Savvides, Marios
Computer Vision and Pattern Recognition
Open-vocabulary object detection (OVD) requires solid modeling of the region-semantic relationship, which could be learned from massive region-text pairs. However, such data is limited in practice due to significant annotation costs. In this work, we propose RTGen to generate scalable open-vocabulary region-text pairs and demonstrate its capability to boost the performance of open-vocabulary object detection. RTGen includes both text-to-region and region-to-text generation processes on scalable image-caption data. The text-to-region generation is powered by image inpainting, directed by our proposed scene-aware inpainting guider for overall layout harmony. For region-to-text generation, we perform multiple region-level image captioning with various prompts and select the best matching text according to CLIP similarity. To facilitate detection training on region-text pairs, we also introduce a localization-aware region-text contrastive loss that learns object proposals tailored with different localization qualities. Extensive experiments demonstrate that our RTGen can serve as a scalable, semantically rich, and effective source for open-vocabulary object detection and continue to improve the model performance when more data is utilized, delivering superior performance compared to the existing state-of-the-art methods.
title RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.19854