Prediction Calibration for Generalized Few-shot Semantic Segmentation

by   Zhihe Lu, et al.

Generalized Few-shot Semantic Segmentation (GFSS) aims to segment each image pixel into either base classes with abundant training examples or novel classes with only a handful of (e.g., 1-5) training images per class. Compared to the widely studied Few-shot Semantic Segmentation FSS, which is limited to segmenting novel classes only, GFSS is much under-studied despite being more practical. Existing approach to GFSS is based on classifier parameter fusion whereby a newly trained novel class classifier and a pre-trained base class classifier are combined to form a new classifier. As the training data is dominated by base classes, this approach is inevitably biased towards the base classes. In this work, we propose a novel Prediction Calibration Network PCN to address this problem. Instead of fusing the classifier parameters, we fuse the scores produced separately by the base and novel classifiers. To ensure that the fused scores are not biased to either the base or novel classes, a new Transformer-based calibration module is introduced. It is known that the lower-level features are useful of detecting edge information in an input image than higher-level features. Thus, we build a cross-attention module that guides the classifier's final prediction using the fused multi-level features. However, transformers are computationally demanding. Crucially, to make the proposed cross-attention module training tractable at the pixel level, this module is designed based on feature-score cross-covariance and episodically trained to be generalizable at inference time. Extensive experiments on PASCAL-5^i and COCO-20^i show that our PCN outperforms the state-the-the-art alternatives by large margins.


page 1

page 2

page 8

page 9

page 10

page 11

page 12


Learning Meta-class Memory for Few-Shot Semantic Segmentation

Currently, the state-of-the-art methods treat few-shot semantic segmenta...

Task-Adaptive Feature Transformer with Semantic Enrichment for Few-Shot Segmentation

Few-shot learning allows machines to classify novel classes using only a...

Weak-shot Semantic Segmentation via Dual Similarity Transfer

Semantic segmentation is an important and prevalent task, but severely s...

Task-Adaptive Feature Transformer for Few-Shot Segmentation

Few-shot learning allows machines to classify novel classes using only a...

Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation

Encouraging progress in few-shot semantic segmentation has been made by ...

Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention

Existing transformer-based image backbones typically propagate feature i...

Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond

Few-shot segmentation (FSS) aims to segment the novel classes with a few...

Please sign up or login with your details

Forgot password? Click here to reset