PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918430480793600 |
|---|---|
| author | Fu, Weifu Li, Jinyang Gao, Bin-Bin Li, Jialin Lin, Yuhuan Deng, Hanqiu Tao, Wenbing Liu, Yong Wang, Chengjie |
| author_facet | Fu, Weifu Li, Jinyang Gao, Bin-Bin Li, Jialin Lin, Yuhuan Deng, Hanqiu Tao, Wenbing Liu, Yong Wang, Chengjie |
| contents | Open-Set Object Detection (OSOD) enables recognition of novel categories beyond fixed classes but faces challenges in aligning text representations with complex visual concepts and the scarcity of image-text pairs for rare categories. This results in suboptimal performance in specialized domains or with complex objects. Recent visual-prompted methods partially address these issues but often involve complex multi-modal designs and multi-stage optimizations, prolonging the development cycle. Additionally, effective training strategies for data-driven OSOD models remain largely unexplored. To address these challenges, we propose PET-DINO, a universal detector supporting both text and visual prompts. Our Alignment-Friendly Visual Prompt Generation (AFVPG) module builds upon an advanced text-prompted detector, addressing the limitations of text representation guidance and reducing the development cycle. We introduce two prompt-enriched training strategies: Intra-Batch Parallel Prompting (IBP) at the iteration level and Dynamic Memory-Driven Prompting (DMD) at the overall training level. These strategies enable simultaneous modeling of multiple prompt routes, facilitating parallel alignment with diverse real-world usage scenarios. Comprehensive experiments demonstrate that PET-DINO exhibits competitive zero-shot object detection capabilities across various prompt-based detection protocols. These strengths can be attributed to inheritance-based philosophy and prompt-enriched training strategies, which play a critical role in building an effective generic object detector. Project page: https://fuweifuvtoo.github.io/pet-dino. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00503 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training Fu, Weifu Li, Jinyang Gao, Bin-Bin Li, Jialin Lin, Yuhuan Deng, Hanqiu Tao, Wenbing Liu, Yong Wang, Chengjie Computer Vision and Pattern Recognition Open-Set Object Detection (OSOD) enables recognition of novel categories beyond fixed classes but faces challenges in aligning text representations with complex visual concepts and the scarcity of image-text pairs for rare categories. This results in suboptimal performance in specialized domains or with complex objects. Recent visual-prompted methods partially address these issues but often involve complex multi-modal designs and multi-stage optimizations, prolonging the development cycle. Additionally, effective training strategies for data-driven OSOD models remain largely unexplored. To address these challenges, we propose PET-DINO, a universal detector supporting both text and visual prompts. Our Alignment-Friendly Visual Prompt Generation (AFVPG) module builds upon an advanced text-prompted detector, addressing the limitations of text representation guidance and reducing the development cycle. We introduce two prompt-enriched training strategies: Intra-Batch Parallel Prompting (IBP) at the iteration level and Dynamic Memory-Driven Prompting (DMD) at the overall training level. These strategies enable simultaneous modeling of multiple prompt routes, facilitating parallel alignment with diverse real-world usage scenarios. Comprehensive experiments demonstrate that PET-DINO exhibits competitive zero-shot object detection capabilities across various prompt-based detection protocols. These strengths can be attributed to inheritance-based philosophy and prompt-enriched training strategies, which play a critical role in building an effective generic object detector. Project page: https://fuweifuvtoo.github.io/pet-dino. |
| title | PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.00503 |