SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation

Abstract

One-shot image semantic segmentation poses a challenging task of recognizing the object regions from unseen categories with only one annotated example as supervision. In this paper, we propose a simple yet effective Similarity Guidance network to tackle the One-shot (SG-One) segmentation problem. We aim at predicting the segmentation mask of a query image with the reference to one densely labeled support image of the same category. To obtain the robust representative feature of the support image, we firstly adopt a masked average pooling strategy for producing the guidance features by only taking the pixels belonging to the support image into account. We then leverage the cosine similarity to build the relationship between the guidance features and features of pixels from the query image. In this way, the possibilities embedded in the produced similarity maps can be adapted to guide the process of segmenting objects. Furthermore, our SG-One is a unified framework which can efficiently process both support and query images within one network and be learned in an end-to-end manner. We conduct extensive experiments on Pascal VOC 2012. In particular, our SGOne achieves the mIoU score of 46.3%, surpassing the baseline methods.

References in corpus (4)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Preserving Semantic Relations for Zero-Shot Learning
• SPGNet: Semantic Prediction Guidance for Scene Parsing

Cited by in corpus (19)

• PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
• Semi-supervised few-shot learning for medical image segmentation
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation
• A Deep One-Shot Network for Query-based Logo Retrieval
• Prototype Mixture Models for Few-shot Semantic Segmentation
• Prototype Refinement Network for Few-Shot Segmentation
• CRNet: Cross-Reference Networks for Few-Shot Segmentation
• Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
• Adaptive Masked Proxies for Few-Shot Segmentation
• FGN: Fully Guided Network for Few-Shot Instance Segmentation
• PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
• Differentiable Meta-learning Model for Few-shot Semantic Segmentation
• Attentional Prototype Inference for Few-Shot Segmentation
• CAFENet: Class-Agnostic Few-Shot Edge Detection Network
• Self-Supervised Tuning for Few-Shot Segmentation
• A New Local Transformation Module for Few-shot Segmentation
• Task-Adaptive Feature Transformer for Few-Shot Segmentation
• A New Few-shot Segmentation Network Based on Class Representation
• End-to-end One-shot Human Parsing