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

Amac, Mustafa Sercan; Sencan, Ahmet; Baran, Orhun Bugra; Ikizler-Cinbis, Nazli; Cinbiş, Ramazan Gökberk

doi:10.1109/wacv51458.2022.00050

Cited by 10 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, researchers started to exploit pixel-level information for FSS, to better utilize support information and align with the dense nature of the task. PGNet (Zhang et al 2019a) and DAN (Wang et al 2020) (Amac et al 2022) extends the self-supervised FSS to general scenarios by using unsupervised saliency prediction to obtain the pseudo-mask of an image. It builds the training task with different splits and augmentations of the pseudo-mask and achieves promising results on the oneshot self-supervised FSS.…”

Section: Related Workmentioning

confidence: 99%

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

Li,

Shi,

Xie

et al. 2024

AAAI

View full text Add to dashboard Cite

The goal of this paper is to alleviate the training cost for few-shot semantic segmentation (FSS) models. Despite that FSS in nature improves model generalization to new concepts using only a handful of test exemplars, it relies on strong supervision from a considerable amount of labeled training data for base classes. However, collecting pixel-level annotations is notoriously expensive and time-consuming, and small-scale training datasets convey low information density that limits test-time generalization. To resolve the issue, we take a pioneering step towards label-efficient training of FSS models from fully unlabeled training data, or additionally a few labeled samples to enhance the performance. This motivates an approach based on a novel unsupervised meta-training paradigm. In particular, the approach first distills pre-trained unsupervised pixel embedding into compact semantic clusters from which a massive number of pseudo meta-tasks is constructed. To mitigate the noise in the pseudo meta-tasks, we further advocate a robust Transformer-based FSS model with a novel prototype-based cross-attention design. Extensive experiments have been conducted on two standard benchmarks, i.e., PASCAL-5i and COCO-20i, and the results show that our method produces impressive performance without any annotations, and is comparable to fully supervised competitors even using only 20% of the annotations. Our code is available at: https://github.com/SSSKYue/UMTFSS.

show abstract

Section: Related Workmentioning

confidence: 99%

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

Li,

Shi,

Xie

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…However, labeling data is a time-consuming and labor-intensive task. To alleviate the dependence of semantic segmentation tasks on labeled data, self-supervised [76] and unsupervised learning [77] can be utilized. These technologies have great research value in image segmentation and can effectively alleviate the problem of poor image analysis results in some fields due to the lack of image segmentation datasets.…”

Section: Self-supervised and Unsupervised Learningmentioning

confidence: 99%

A Survey on Image Semantic Segmentation Using Deep Learning Techniques

Cheng¹,

Li²,

Li³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Image semantic segmentation is an important branch of computer vision of a wide variety of practical applications such as medical image analysis, autonomous driving, virtual or augmented reality, etc. In recent years, due to the remarkable performance of transformer and multilayer perceptron (MLP) in computer vision, which is equivalent to convolutional neural network (CNN), there has been a substantial amount of image semantic segmentation works aimed at developing different types of deep learning architecture. This survey aims to provide a comprehensive overview of deep learning methods in the field of general image semantic segmentation. Firstly, the commonly used image segmentation datasets are listed. Next, extensive pioneering works are deeply studied from multiple perspectives (e.g., network structures, feature fusion methods, attention mechanisms), and are divided into four categories according to different network architectures: CNN-based architectures, transformer-based architectures, MLP-based architectures, and others. Furthermore, this paper presents some common evaluation metrics and compares the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value on the most widely used datasets. Finally, possible future research directions and challenges are discussed for the reference of other researchers.

show abstract