DeepAI AI Chat
Log In Sign Up

Cross-domain Few-shot Segmentation with Transductive Fine-tuning

by   Yuhang Lu, et al.

Few-shot segmentation (FSS) expects models trained on base classes to work on novel classes with the help of a few support images. However, when there exists a domain gap between the base and novel classes, the state-of-the-art FSS methods may even fail to segment simple objects. To improve their performance on unseen domains, we propose to transductively fine-tune the base model on a set of query images under the few-shot setting, where the core idea is to implicitly guide the segmentation of query images using support labels. Although different images are not directly comparable, their class-wise prototypes are desired to be aligned in the feature space. By aligning query and support prototypes with an uncertainty-aware contrastive loss, and using a supervised cross-entropy loss and an unsupervised boundary loss as regularizations, our method could generalize the base model to the target domain without additional labels. We conduct extensive experiments under various cross-domain settings of natural, remote sensing, and medical images. The results show that our method could consistently and significantly improve the performance of prototypical FSS models in all cross-domain tasks.


page 4

page 5

page 8

page 9

page 10


Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification

Cross-domain few-shot classification induces a much more challenging pro...

Feature Transformation for Cross-domain Few-shot Remote Sensing Scene Classification

Effectively classifying remote sensing scenes is still a challenge due t...

RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Network

Cross-domain few-shot segmentation (CD-FSS) aims to achieve semantic seg...

Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation

Few-shot classification aims to recognize novel categories with only few...

Dense Affinity Matching for Few-Shot Segmentation

Few-Shot Segmentation (FSS) aims to segment the novel class images with ...

Unsupervised Cross-domain Pulmonary Nodule Detection without Source Data

Cross domain pulmonary nodule detection suffers from performance degrada...

Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?

Few-shot segmentation has recently attracted substantial interest, with ...