Few-shot segmentation (FSS) aims at performing semantic segmentation on novel classes given a few annotated support samples. With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head. Due to the intricacy of the decoder and its matching pipeline, it is not easy to follow such an FSS framework. This paper revives the straightforward framework of "feature extractor $+$ linear classification head" and proposes a novel Feature-Proxy Transformer (FPTrans) method, in which the "proxy" is the vector representing a semantic class in the linear classification head. FPTrans has two keypoints for learning discriminative features and representative proxies: 1) To better utilize the limited support samples, the feature extractor makes the query interact with the support features from the bottom to top layers using a novel prompting strategy. 2) FPTrans uses multiple local background proxies (instead of a single one) because the background is not homogeneous and may contain some novel foreground regions. These two keypoints are easily integrated into the vision transformer backbone with the prompting mechanism in the transformer. Given the learned features and proxies, FPTrans directly compares their cosine similarity for segmentation. Although the framework is straightforward, we show that FPTrans achieves competitive FSS accuracy on par with state-of-the-art decoder-based methods.
翻译:少截分法( FSS ) 旨在对新类进行语义分解, 并给出一些附加注释的支持样本 。 通过重新思考最近的进展, 我们发现目前的 FSS 框架已经偏离了监督的分解框架 : 鉴于这些深度特征, FSS 方法通常使用复杂的解析器来进行精密的像素匹配, 而受监督的分解方法则使用简单的线性分类头。 由于解析器及其匹配管道的复杂性, 遵循这样的 FSS 框架并不容易。 本文恢复了“ 直径提取器 $+$ 线性分类头” 的直截框架, 并且提出了一个新的 FSS 系统框架, 并且提出了一个新的 功能- 质质谱转换器( FPTranser ) 方法, 其中, “ pressorx” 是代表线性分类头的语义类的矢量。 FRS 有两个关键点 。 为了更好地利用有限的支持样本,, 特性提取器与从下层到顶层的支持特性框架互动。 2, FPtransrence 使用多种直截面的直截面,, 直截面的直截面显示为直截面,,,, 直截面的直截面的直截面,,, 显示为 直直截面,,, 直地显示为 直路路路路路路为,,,,, 直路路路路路路路路路路路,,, 。