paper-with-me

Papers

MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation

2021-10-23 · Mustafa Sercan Amac, Ahmet Sencan, Orhun Bugra Baran, Nazli Ikizler-Cinbis, Ramazan Gokberk Cinbis

Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though the few-shot setting reduces this cost for novel test classes, there is still a need to annotate the training data. To alleviate this need, we propose a self-supervised training approach for learning few-shot segmentation models. We first use unsupervised saliency estimation to obtain pseudo-masks on images. We then train a simple prototype based model over different splits of pseudo masks and augmentations of images. Our extensive experiments show that the proposed approach achieves promising results, highlighting the potential of self-supervised training. To the best of our knowledge this is the first work that addresses unsupervised few-shot segmentation problem on natural images.

📄 PDF Abstract BibTeX arXiv:2110.12207

Code (1)

AhmetSencan/MaskSplit-Self-supervised-Meta-learning-for-Few-shot-Semantic-Segmentation pytorch

Tasks

Few-Shot LearningFew-Shot Semantic SegmentationMeta-LearningSaliency PredictionSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Are Few-shot Learning Benchmarks Too Simple ?

2019-09-25 · Gabriel Huang, Hugo Larochelle, Simon Lacoste-Julien

We argue that the widely used Omniglot and miniImageNet benchmarks are too simple because their class semantics do not vary across episodes, which defeats their intended purpose of evaluating few-shot classification meth…

ClassificationFew-Shot Learning

On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting

2022-04-01 · Wei-Tsung Kao, Yuan-Kuei Wu, Chia-Ping Chen, Zhi-Sheng Chen 외

User-defined keyword spotting is a task to detect new spoken terms defined by users. This can be viewed as a few-shot learning problem since it is unreasonable for users to define their desired keywords by providing many…

Few-Shot LearningKeyword SpottingMeta-LearningSelf-Supervised Learning

Few-Shot Image Classification via Contrastive Self-Supervised Learning

2020-08-23 · Jianyi Li, Guizhong Liu

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. I…

ClassificationFew-Shot Image ClassificationFew-Shot LearningGeneral Classification+5

Trainable Class Prototypes for Few-Shot Learning

2021-06-21 · Jianyi Li, Guizhong Liu

Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the ar…

Few-Shot LearningMetric LearningSelf-Supervised LearningUnsupervised Few-Shot Image Classification+1

Self-Supervised Prototypical Transfer Learning for Few-Shot Classification

2020-06-19 · Carlos Medina, Arnout Devos, Matthias Grossglauser

Most approaches in few-shot learning rely on costly annotated data related to the goal task domain during (pre-)training. Recently, unsupervised meta-learning methods have exchanged the annotation requirement for a reduc…

ClassificationFew-Shot LearningGeneral ClassificationMeta-Learning+4