Learning to Prompt Segment Anything Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911752462008320 |
|---|---|
| author | Huang, Jiaxing Jiang, Kai Zhang, Jingyi Qiu, Han Lu, Lewei Lu, Shijian Xing, Eric |
| author_facet | Huang, Jiaxing Jiang, Kai Zhang, Jingyi Qiu, Han Lu, Lewei Lu, Shijian Xing, Eric |
| contents | Segment Anything Models (SAMs) like SEEM and SAM have demonstrated great potential in learning to segment anything. The core design of SAMs lies with Promptable Segmentation, which takes a handcrafted prompt as input and returns the expected segmentation mask. SAMs work with two types of prompts including spatial prompts (e.g., points) and semantic prompts (e.g., texts), which work together to prompt SAMs to segment anything on downstream datasets. Despite the important role of prompts, how to acquire suitable prompts for SAMs is largely under-explored. In this work, we examine the architecture of SAMs and identify two challenges for learning effective prompts for SAMs. To this end, we propose spatial-semantic prompt learning (SSPrompt) that learns effective semantic and spatial prompts for better SAMs. Specifically, SSPrompt introduces spatial prompt learning and semantic prompt learning, which optimize spatial prompts and semantic prompts directly over the embedding space and selectively leverage the knowledge encoded in pre-trained prompt encoders. Extensive experiments show that SSPrompt achieves superior image segmentation performance consistently across multiple widely adopted datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04651 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning to Prompt Segment Anything Models Huang, Jiaxing Jiang, Kai Zhang, Jingyi Qiu, Han Lu, Lewei Lu, Shijian Xing, Eric Computer Vision and Pattern Recognition Segment Anything Models (SAMs) like SEEM and SAM have demonstrated great potential in learning to segment anything. The core design of SAMs lies with Promptable Segmentation, which takes a handcrafted prompt as input and returns the expected segmentation mask. SAMs work with two types of prompts including spatial prompts (e.g., points) and semantic prompts (e.g., texts), which work together to prompt SAMs to segment anything on downstream datasets. Despite the important role of prompts, how to acquire suitable prompts for SAMs is largely under-explored. In this work, we examine the architecture of SAMs and identify two challenges for learning effective prompts for SAMs. To this end, we propose spatial-semantic prompt learning (SSPrompt) that learns effective semantic and spatial prompts for better SAMs. Specifically, SSPrompt introduces spatial prompt learning and semantic prompt learning, which optimize spatial prompts and semantic prompts directly over the embedding space and selectively leverage the knowledge encoded in pre-trained prompt encoders. Extensive experiments show that SSPrompt achieves superior image segmentation performance consistently across multiple widely adopted datasets. |
| title | Learning to Prompt Segment Anything Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.04651 |