DeepAI AI Chat
Log In Sign Up

Attentional Prototype Inference for Few-Shot Semantic Segmentation

by   Haoliang Sun, et al.
Shandong University
Beihang University
University of Amsterdam

This paper aims to address few-shot semantic segmentation. While existing prototype-based methods have achieved considerable success, they suffer from uncertainty and ambiguity caused by limited labelled examples. In this work, we propose attentional prototype inference (API), a probabilistic latent variable framework for few-shot semantic segmentation. We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution. The probabilistic modeling of the prototype enhances the model's generalization ability by handling the inherent uncertainty caused by limited data and intra-class variations of objects. To further enhance the model, we introduce a local latent variable to represent the attention map of each query image, which enables the model to attend to foreground objects while suppressing background. The optimization of the proposed model is formulated as a variational Bayesian inference problem, which is established by amortized inference networks.We conduct extensive experiments on three benchmarks, where our proposal obtains at least competitive and often better performance than state-of-the-art methods. We also provide comprehensive analyses and ablation studies to gain insight into the effectiveness of our method for few-shot semantic segmentation.


page 6

page 8

page 9

page 10

page 11


SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes

Few-shot semantic segmentation aims to segment novel-class objects in a ...

Part-aware Prototype Network for Few-shot Semantic Segmentation

Few-shot semantic segmentation aims to learn to segment new object class...

Prototype Mixture Models for Few-shot Semantic Segmentation

Few-shot segmentation is challenging because objects within the support ...

Generalized Few-Shot Semantic Segmentation

Training semantic segmentation models requires a large amount of finely ...

Self-Support Few-Shot Semantic Segmentation

Existing few-shot segmentation methods have achieved great progress base...

Interclass Prototype Relation for Few-Shot Segmentation

Traditional semantic segmentation requires a large labeled image dataset...

A Tutorial on Probabilistic Latent Semantic Analysis

In this tutorial, I will discuss the details about how Probabilistic Lat...