Related papers: SemiGDA: Generative Dual-distribution Alignment fo…

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…

Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual…

Weak-strong consistency learning strategies are widely employed in semi-supervised medical image segmentation to train models by leveraging limited labeled data and enforcing weak-to-strong consistency. However, existing methods primarily…

The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled…

Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…

Unsupervised domain adaptation for semantic segmentation (DASS) aims to transfer knowledge from a label-rich source domain to a target domain with no labels. Two key approaches in DASS are (1) vision-only approaches using masking or…

Segment anything model (SAM) has emerged as the leading approach for zero-shot learning in segmentation tasks, offering the advantage of avoiding pixel-wise annotations. It is particularly appealing in medical image segmentation, where the…

Automatic histopathology image segmentation is crucial to disease analysis. Limited available labeled data hinders the generalizability of trained models under the fully supervised setting. Semi-supervised learning (SSL) based on generative…

Unlike images and natural language tokens, time series data is highly semantically sparse, resulting in labor-intensive label annotations. Unsupervised and Semi-supervised Domain Adaptation (UDA and SSDA) have demonstrated efficiency in…

In semi-supervised domain adaptation (SSDA), the model aims to leverage partially labeled target domain data along with a large amount of labeled source domain data to enhance its generalization capability for the target domain. A key…

Semi-supervised semantic segmentation aims to utilize limited labeled images and abundant unlabeled images to achieve label-efficient learning, wherein the weak-to-strong consistency regularization framework, popularized by FixMatch, is…

Despite their effectiveness, current deep learning models face challenges with images coming from different domains with varying appearance and content. We introduce SegCLR, a versatile framework designed to segment images across different…

Semi-supervised learning (semi-SL) is a promising alternative to supervised learning for medical image analysis when obtaining good quality supervision for medical imaging is difficult. However, semi-SL assumes that the underlying…

Semi-supervised Domain Generalization (SSDG) addresses the challenge of generalizing to unseen target domains with limited labeled data. Existing SSDG methods highlight the importance of achieving high pseudo-labeling (PL) accuracy and…

We bring a new perspective to semi-supervised semantic segmentation by providing an analysis on the labeled and unlabeled distributions in training datasets. We first figure out that the distribution gap between labeled and unlabeled…

Recently, machine learning-based semantic segmentation algorithms have demonstrated their potential to accurately segment regions and contours in medical images, allowing the precise location of anatomical structures and abnormalities.…

Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation…

Standard segmentation of medical images based on full-supervised convolutional networks demands accurate dense annotations. Such learning framework is built on laborious manual annotation with restrict demands for expertise, leading to…

Studies on semi-supervised medical image segmentation (SSMIS) have seen fast progress recently. Due to the limited labelled data, SSMIS methods mainly focus on effectively leveraging unlabeled data to enhance the segmentation performance.…

Medical image segmentation is a critical step in computer-aided diagnosis, and convolutional neural networks are popular segmentation networks nowadays. However, the inherent local operation characteristics make it difficult to focus on the…