Home

Awesome

MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation

This is the official implementation of the paper MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation

Authors: Ehtesham Iqbal, Sirojbek Safarov, Seongdeok Bang

Abstract: Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. Prototype learning, where the support feature yields a singleor several prototypes by averaging global and local object information, has been widely used in FSS. However, utilizing only prototype vectors may be insufficient to represent the features for all training data. To extract abundant features and make more precise predictions, we propose a Multi-Similarity and Attention Network (MSANet) including two novel modules, a multi-similarity module and an attention module. The multi-similarity module exploits multiple feature maps of support images and query images to estimate accurate semantic relationships. The attention module instructs the network to concentrate on class-relevant information. The network is tested on standard FSS datasets, PASCAL-5i 1-shot, PASCAL-5i 5-shot, COCO-20i 1-shot, and COCO-20i 5-shot. The MSANet with the backbone of ResNet-101 achieves the state-of-the-art performance for all 4-benchmark datasets with mean intersection over union (mIoU) of 69.13%, 73.99%, 51.09%, 56.80%, respectively.

<p align="middle"> <img src="figure/Main.png"> </p>

Dependencies

Datasets

Download PASCAL, COCO and Base annotation dataset and put in MSANet/data directrory.

Models

Scripts

Performance

Performance comparison with the state-of-the-art approaches (i.e., HSNet, BAM and VAT in terms of average mIoU across all folds.

  1. PASCAL-5<sup>i</sup>
    BackboneMethod1-shot5-shot
    VGG16BAM64.4168.76
    MSANet(ours)65.76 <sub>(+1.35)</sub>70.40 <sub>(+1.64)</sub>
    ResNet50BAM67.8170.91
    MSANet(ours)68.52 <sub>(+0.71)</sub>72.60 <sub>(+1.69)</sub>
    ResNet101VAT67.5071.60
    MSANet(ours)69.13 <sub>(+1.63)</sub>73.99 <sub>(+2.39)</sub>
  2. COCO-20<sup>i</sup>
    BackboneMethod1-shot5-shot
    ResNet50BAM46.2351.16
    MSANet(ours)48.03 <sub>(+1.8)</sub>53.67 <sub>(+2.51)</sub>
    ResNet101HSNet41.2049.50
    MSANet(ours)51.09 <sub>(+9.89)</sub>56.80 <sub>(+7.30)</sub>

Visualization

<p align="middle"> <img src="figure/visual.png"> </p>

References

This repo is mainly built based on PFENet, HSNet, and BAM. Thanks for their great work!

### BibTeX
If you find this research useful, please consider citing:
````BibTeX
@article{MSANet2022,
  title={MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation},
  author={Ehtesham Iqbal, Sirojbek Safarov, Seongdeok Bang},
  journal={arXiv preprint arXiv:2206.09667},
  year={2022}
}