keyword
semi-supervised segmentation
Semi-supervised segmentation is a machine learning approach in computer vision that divides images into meaningful regions or pixel-level categories by training on a small amount of accurately labeled data combined with a larger volume of unlabeled or partially annotated data. This paradigm addresses the high cost and labor required to produce detailed, pixel-by-pixel ground-truth annotations across entire datasets. By exploiting underlying structures, feature distributions, or auxiliary information contained within the unlabeled data through techniques such as consistency training, contrastive learning, and pseudo-labeling, semi-supervised segmentation models achieve high boundary precision and semantic accuracy while significantly reducing the dependency on extensive manual labeling.
2 items
Cross-patch Dense Contrastive Learning for Semi-supervised Segmentation of Cellular Nuclei in Histopathologic Images
Huisi Wu, Zhaoze Wang, Youyi Song, Lin Yang, Jing Qin
Why you should read this
Proposes a cross-patch dense contrastive learning framework that pairs patch- and pixel-level representations within a mean-teacher architecture to segment cellular nuclei accurately from limited annotated histopathology images.
We study the semi-supervised learning problem, using a few labeled data and a large amount of unlabeled data to train the network, by developing a cross-patch dense contrastive learning framework, to segment cellular nuclei in histopathologic images. This task is motivated by the expensive burden on collecting labeled data for histopathologic image segmentation tasks. The key idea of our method is to align features of teacher and student networks, sampled from cross-image in both patch- and pixel-levels, for enforcing the intra-class compactness and inter-class separability of features that as we shown is helpful for extracting valuable knowledge from unlabeled data. We also design a novel optimization framework that combines consistency regularization and entropy minimization techniques, showing good property in eviction of gradient vanishing. We assess the proposed method on two publicly available datasets, and obtain positive results on extensive experiments, outperforming the state-of-the-art methods. Codes are available at https://github.com/zzw-szu/CDCL.
Added
2026-09-26
Connecting Modalities: Semi-supervised Segmentation and Annotation of Images Using Unaligned Text Corpora
Richard Socher, Li Fei-Fei
Why you should read this
Demonstrates how to train image segmentation and annotation systems using only a handful of labeled images and freely available news articles by discovering that visual regions and text words follow similar contextual patterns, enabling efficient learning without massive labeled datasets.
We propose a semi-supervised model which segments and annotates images using very few labeled images and a large unaligned text corpus to relate image regions to text labels. Given photos of a sports event, all that is necessary to provide a pixel-level labeling of objects and background is a set of newspaper articles about this sport and one to five labeled images. Our model is motivated by the observation that words in text corpora share certain context and feature similarities with visual objects. We describe images using visual words, a new region-based representation. The proposed model is based on kernelized canonical correlation analysis which finds a mapping between visual and textual words by projecting them into a latent meaning space. Kernels are derived from context and adjective features inside the respective visual and textual domains. We apply our method to a challenging dataset and rely on articles of the New York Times for textual features. Our model outperforms the state-of-the-art in annotation. In segmentation it compares favorably with other methods that use significantly more labeled training data.
Added
2026-02-21