MFP: Making Full Use of Probability Maps for Interactive Image Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913345677819904 |
|---|---|
| author | Lee, Chaewon Lee, Seon-Ho Kim, Chang-Su |
| author_facet | Lee, Chaewon Lee, Seon-Ho Kim, Chang-Su |
| contents | In recent interactive segmentation algorithms, previous probability maps are used as network input to help predictions in the current segmentation round. However, despite the utilization of previous masks, useful information contained in the probability maps is not well propagated to the current predictions. In this paper, to overcome this limitation, we propose a novel and effective algorithm for click-based interactive image segmentation, called MFP, which attempts to make full use of probability maps. We first modulate previous probability maps to enhance their representations of user-specified objects. Then, we feed the modulated probability maps as additional input to the segmentation network. We implement the proposed MFP algorithm based on the ResNet-34, HRNet-18, and ViT-B backbones and assess the performance extensively on various datasets. It is demonstrated that MFP meaningfully outperforms the existing algorithms using identical backbones. The source codes are available at https://github.com/cwlee00/MFP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18448 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MFP: Making Full Use of Probability Maps for Interactive Image Segmentation Lee, Chaewon Lee, Seon-Ho Kim, Chang-Su Computer Vision and Pattern Recognition In recent interactive segmentation algorithms, previous probability maps are used as network input to help predictions in the current segmentation round. However, despite the utilization of previous masks, useful information contained in the probability maps is not well propagated to the current predictions. In this paper, to overcome this limitation, we propose a novel and effective algorithm for click-based interactive image segmentation, called MFP, which attempts to make full use of probability maps. We first modulate previous probability maps to enhance their representations of user-specified objects. Then, we feed the modulated probability maps as additional input to the segmentation network. We implement the proposed MFP algorithm based on the ResNet-34, HRNet-18, and ViT-B backbones and assess the performance extensively on various datasets. It is demonstrated that MFP meaningfully outperforms the existing algorithms using identical backbones. The source codes are available at https://github.com/cwlee00/MFP. |
| title | MFP: Making Full Use of Probability Maps for Interactive Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.18448 |