Segment object with few examples by unshared feature and target-similar feature score with TBSNet
Segment object with few examples by unshared feature and target-similar feature score with TBSNet
Task-Disruptive Background Suppression for Few-Shot Segmentation
arXiv paper abstract https://arxiv.org/abs/2312.15894
arXiv PDF paper https://arxiv.org/pdf/2312.15894.pdf
Few-shot segmentation aims to accurately segment novel target objects within query images using only a limited number of annotated support images.
... background ... problematic ... as follows: (1) when the query and support backgrounds are dissimilar and (2) when objects in the support background are similar to the target object in the query.
... propose Task-disruptive Background Suppression (TBS) ... to suppress those disruptive support background features based on two spatial-wise scores: query-relevant and target-relevant scores.
The former aims to mitigate the impact of unshared features solely existing in the support background, while the latter aims to reduce the influence of target-similar support background features.
... these two scores, ... define a query background relevant score that captures the similarity between the backgrounds of the query and the support, and utilize it to scale support background features to adaptively restrict the impact of disruptive support backgrounds.
... proposed method achieves state-of-the-art performance ... on 1-shot segmentation ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments