# A New Local Transformation Module for Few-shot Segmentation

arXiv: https://arxiv.org/abs/1910.05886 · HTML: https://mlsanity.com/paper/1910.05886/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2019.

## Built on by (most cited first, 15 of 15)

- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation](https://mlsanity.com/paper/2208.00306/) (2022)
- [Dense Gaussian Processes for Few-Shot Segmentation](https://mlsanity.com/paper/2110.03674/) (2021)
- [Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overview](https://mlsanity.com/paper/2211.08352/) (2022)
- [FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter](https://mlsanity.com/paper/2104.00073/) (2021)
- [A survey on IQA](https://mlsanity.com/paper/2109.00347/) (2021)
- [Language bias in Visual Question Answering: A Survey and Taxonomy](https://mlsanity.com/paper/2111.08531/) (2021)
- [Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges](https://mlsanity.com/paper/2304.05832/) (2023)
- [Few-shot semantic segmentation via mask aggregation](https://mlsanity.com/paper/2202.07231/) (2022)
- [Deep Gaussian Processes for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16549/) (2021)
- [A Review of 3D Face Reconstruction From a Single Image](https://mlsanity.com/paper/2110.09299/) (2021)
- [Prototypical Region Proposal Networks for Few-Shot Localization and Classification](https://mlsanity.com/paper/2104.03496/) (2021)
- [A Review of Deep Learning Based Image Super-resolution Techniques](https://mlsanity.com/paper/2201.10521/) (2022)

## Abstract (arXiv)

Few-shot segmentation segments object regions of new classes with a few of manual annotations. Its key step is to establish the transformation module between support images (annotated images) and query images (unlabeled images), so that the segmentation cues of support images can guide the segmentation of query images. The existing methods form transformation model based on global cues, which however ignores the local cues that are verified in this paper to be very important for the transformation. This paper proposes a new transformation module based on local cues, where the relationship of the local features is used for transformation. To enhance the generalization performance of the network, the relationship matrix is calculated in a high-dimensional metric embedding space based on cosine distance. In addition, to handle the challenging mapping problem from the low-level local relationships to high-level semantic cues, we propose to apply generalized inverse matrix of the annotation matrix of support images to transform the relationship matrix linearly, which is non-parametric and class-agnostic. The result by the matrix transformation can be regarded as an attention map with high-level semantic cues, based on which a transformation module can be built simply.The proposed transformation module is a general module that can be used to replace the transformation module in the existing few-shot segmentation frameworks. We verify the effectiveness of the proposed method on Pascal VOC 2012 dataset. The value of mIoU achieves at 57.0% in 1-shot and 60.6% in 5-shot, which outperforms the state-of-the-art method by 1.6% and 3.5%, respectively.