Unsupervised Image Segmentation Research Articles

Unsupervised Image Segmentation on 2D Echocardiogram

Echocardiography is a widely used, non-invasive imaging technique for diagnosing and monitoring heart conditions. However, accurate segmentation of cardiac structures, particularly the left ventricle, remains a complex task due to the inherent variability and noise in echocardiographic images. Current supervised models have achieved state-of-the-art results but are highly dependent on large, annotated datasets, which are costly and time-consuming to obtain and depend on the quality of the annotated data. These limitations motivate the need for unsupervised methods that can generalize across different image conditions without relying on annotated data. In this study, we propose an unsupervised approach for segmenting 2D echocardiographic images. By combining customized objective functions with convolutional neural networks (CNNs), our method effectively segments cardiac structures, addressing the challenges posed by low-resolution and gray-scale images. Our approach leverages techniques traditionally used outside of medical imaging, optimizing feature extraction through CNNs in a data-driven manner and with a new and smaller network design. Another key contribution of this work is the introduction of a post-processing algorithm that refines the segmentation to isolate the left ventricle in both diastolic and systolic positions, enabling the calculation of the ejection fraction (EF). This calculation serves as a benchmark for evaluating the performance of our unsupervised method. Our results demonstrate the potential of unsupervised learning to improve echocardiogram analysis by overcoming the limitations of supervised approaches, particularly in settings where labeled data are scarce or unavailable.

DynaSeg: A deep dynamic fusion method for unsupervised image segmentation incorporating feature similarity and spatial continuity

Our work tackles the fundamental challenge of image segmentation in computer vision, which is crucial for diverse applications. While supervised methods demonstrate proficiency, their reliance on extensive pixel-level annotations limits scalability. We introduce DynaSeg, an innovative unsupervised image segmentation approach that overcomes the challenge of balancing feature similarity and spatial continuity without relying on extensive hyperparameter tuning. Unlike traditional methods, DynaSeg employs a dynamic weighting scheme that automates parameter tuning, adapts flexibly to image characteristics, and facilitates easy integration with other segmentation networks. By incorporating a Silhouette Score Phase, DynaSeg prevents undersegmentation failures where the number of predicted clusters might converge to one. DynaSeg uses CNN-based and pre-trained ResNet feature extraction, making it computationally efficient and more straightforward than other complex models. Experimental results showcase state-of-the-art performance, achieving a 12.2% and 14.12% mIOU improvement over current unsupervised segmentation approaches on COCO-All and COCO-Stuff datasets, respectively. We provide qualitative and quantitative results on five benchmark datasets, demonstrating the efficacy of the proposed approach. Code available at \\url{https://github.com/RyersonMultimediaLab/DynaSeg}

A multibranch and multiscale neural network based on semantic perception for multimodal medical image fusion

Medical imaging is indispensable for accurate diagnosis and effective treatment, with modalities like MRI and CT providing diverse yet complementary information. Traditional image fusion methods, while essential in consolidating information from multiple modalities, often suffer from poor image quality and loss of crucial details due to inadequate handling of semantic information and limited feature extraction capabilities. This paper introduces a novel medical image fusion technique leveraging unsupervised image segmentation to enhance the semantic understanding of the fusion process. The proposed method, named DUSMIF, employs a multi-branch, multi-scale deep learning architecture that integrates advanced attention mechanisms to refine the feature extraction and fusion processes. An innovative approach that utilizes unsupervised image segmentation to extract semantic information is introduced, which is then integrated into the fusion process. This not only enhances the semantic relevance of the fused images but also improves the overall fusion quality. The paper proposes a sophisticated network structure that extracts and fuses features at multiple scales and across multiple branches. This structure is designed to capture a comprehensive range of image details and contextual information, significantly improving the fusion outcomes. Multiple attention mechanisms are incorporated to selectively emphasize important features and integrate them effectively across different modalities and scales. This approach ensures that the fused images maintain high quality and detail fidelity. A joint loss function combining content loss, structural similarity loss, and semantic loss is formulated. This function not only guides the network in preserving image brightness and texture but also ensures that the fused image closely resembles the source images in both content and structure. The proposed method demonstrates superior performance over existing fusion techniques in objective assessments and subjective evaluations, confirming its effectiveness in enhancing the diagnostic utility of fused medical images.

Assessing readability of the text in ancient paper fragments by a photometric statistical analysis

Ancient documents are important historical sources that are often found in a fragmented condition due to their conservation status. In this study, we examined fragments of paper found in 1996 during excavation of theSanti Quattro Coronaticomplex, in Rome. The archaeological site where the fragments were found is situated on the first floor of the tower within the complex. This location was used as a disposal pit approximately between the 15th and 16th centuries. The fragments exhibit text discoloration, hindering automatic recognition and human readability. To reveal the faded text, the fragments have been digitalized, converted into a perceptually uniform color space and the contrast has been enhanced. The photometric characteristics of the input and enhanced images have been statistically characterized, and the contrast enhancement assessed by a state-of-the-art metric. The statistical analysis of the text colour coordinates was carried out to develop supervised and unsupervised image segmentation, isolating the text.The results of the method show that it effectively identifies text regions within images, improving readability, even for faded text. It can be integrated into deep learning-based character recognition systems, facilitating the automatic analysis of historical handwritten documents.

A new commercial boundary dataset for metropolitan areas in the USA and Canada, built from open data

The purpose of this study is to define the geographic boundaries of commercial areas by creating a consistent definition, combining various commercial area types, including downtowns, retail centres, financial districts, and other employment subcentres. Our research involved the collection of office, retail and job density data from 69 metropolitan regions across USA and Canada. Using this data, we conducted an unsupervised image segmentation model and clustering methods to identify distinctive commercial geographic boundaries. As a result, we identified 23,751 commercial areas, providing a detailed perspective on the commercial landscape of metropolitan areas in the USA and Canada. In addition, the generated boundaries were successfully validated through comparison with previously established commerce-related boundaries. The output of this study has implications for urban and regional planning and economic development, delivering valuable insights into the overall commercial geography in the region. The commercial boundary and used codes are freely available on the School of Cities Github, and users can reuse, reproduce and modify the boundaries.

Differentiable double clustering with edge-aware superpixel fitting for unsupervised image segmentation

Unsupervised image segmentation is an essential topic in the field of computer vision, which broke the limitation of training data and expanded application scenarios. Off-the-shelf clustering methods simply rely on semantic concepts and incomplete boundary cues, resulting in incorrect segmentation in object boundaries. Therefore, this paper proposes an unsupervised image segmentation framework combining differentiable double clustering (DDC) and edge-aware superpixel (EA), which outperform prior work on the accuracy of the prior art. First, a multi-layer feature extraction network is introduced to combine low-level and high-level features for clustering. Then, the DDC module is designed to obtain initial labels of pixels from both local and global perspectives to improve the clustering accuracy. Pixel-wise feature similarity in different classes is pushed away, and one in the same class is brought closer. Finally, we use EA to provide well-fitting boundary cues for DDC label fusion to reduce incorrect segmentation. Extensive experiments on the benchmark datasets PASCAL VOC2012 [34] and BSD500 demonstrate that the proposed method provides competitive segmentation results.

Automatic Marker Generation to Similarity Based Region Merging Algorithm using Edge Information

One of the most important tasks in computer vision is image segmentation. Several interactive strategies are utilized for picture segmentation because automated techniques are difficult for this kind of work. The outcome of interactive methods is mostly determined by user input. Obtaining excellent interactions for huge datasets is challenging. However, automated picture segmentation is starting to play a significant role in image analysis and computer vision. Effective and efficient segmentation outcomes are obtained using the interacting region merging method suggested by Maximal Similarity based region merging algorithm. Limitation of MSBRM is it requires some efforts on the part of users and is yet not a fully-automatic approach. Here, we suggest a completely fresh unsupervised image segmentation method that combines edge information with MSBRM. We propose an integrated framework to generate object markers for similarity based region algorithm using edge information. Long edges give rough distribution of objects in image. After retrieving edges using phase congruency, edge processing operations are employed to remove small edges and to group color similar long boundaries. Centroids of long boundaries are used as object markers to the MSBRM algorithm. The generation of object markers is done using edge segment grouping. These object markers guide the region merging process. The proposed method shows its effectiveness in segmenting natural real world color images.

Ensemble CART surrogate-assisted automatic multi-objective rough fuzzy clustering algorithm for unsupervised image segmentation

Multi-objective clustering algorithms (MOCAs) are popular in unsupervised image segmentation due to their merit of meeting multiple segmentation requirements and the prospect of automatically estimating the number of clusters. However, most of them suffer from high time costs and are easily to be influenced by the uncertainty when handling real complex images. To address these issues, we propose an ensemble classification and regression tree (CART) surrogate-assisted automatic multi-objective rough fuzzy clustering (ECS-AMRFC) algorithm for unsupervised image segmentation. Firstly, a cluster medoid-based encoding scheme is employed to represent solutions with different number of clusters and meanwhile lessen the length of encoding. Then, we design an ensemble CART as the surrogate model to significantly reduce the computational burden. Moreover, a surrogate model management strategy is proposed to accelerate the optimization and enhance the quality of surrogate modeling. To handle the uncertainty in data, we extend the rough fuzzy clustering into MOCAs and construct three complementary objective functions to seek proper cluster medoids from multiple perspectives. In addition, the Gaussian kernel is introduced into the objective functions to handle image pixels that cannot separate linearly in the feature space. Finally, a kernelized rough fuzzy clustering validity index is defined to automatically select the optimal solution with no requirements of any prior knowledge. Experiments show that ECS-AMRFC not only identifies appropriate number of clusters on different kinds of images, but also obtains better segmentation results than state-of-the-art rough fuzzy clustering algorithms and automatic MOCAs.

A guide to unsupervised image segmentation of mCT-scanned cellular metals with mixture modelling and Markov random fields

Characterising the structure of cellular metals is a difficult task. The internal structure of cellular metals can be determined using micro-computed tomography (mCT). However, mCT scanning provides digital images in greyscale with various problematic artefacts. In addition, the grey intensity of cellular metals usually varies greatly due to the internal porosity of the material. Therefore, binary image segmentation to extract material segments from digital images is quite difficult. Our contribution can be summarised as follows. A comprehensive evaluation of various mixture models that have been shown in the literature to be useful for tomography, but for the purpose of binary image segmentation of cellular metals and internal porosity assessment. We propose a novel merging technique to merge different components of the mixture model for the purpose of binary image segmentation of cellular metals. Finally, to enforce spatial regularisation and further improve the binary image segmentation, we combine the obtained two-segment mixture model (material-void mixture model) with Markov random fields and evaluate the effects of different strengths of spatial regularisation. Our proposals are thoroughly investigated using five different types of cellular metals. The reported results are promising and competitive and speak in favour of the relevance of our proposals.

Adaptive Segmentation Algorithm for Subtle Defect Images on the Surface of Magnetic Ring Using 2D-Gabor Filter Bank

In order to realize the unsupervised segmentation of subtle defect images on the surface of small magnetic rings and improve the segmentation accuracy and computational efficiency, here, an adaptive threshold segmentation method is proposed based on the improved multi-scale and multi-directional 2D-Gabor filter bank. Firstly, the improved multi-scale and multi-directional 2D-Gabor filter bank was used to filter and reduce the noise on the defect image, suppress the noise pollution inside the target area and the background area, and enhance the difference between the magnetic ring defect and the background. Secondly, this study analyzed the grayscale statistical characteristics of the processed image; the segmentation threshold was constructed according to the gray statistical law of the image; and the adaptive segmentation of subtle defect images on the surface of small magnetic rings was realized. Finally, a classifier based on a BP neural network is designed to classify the scar images and crack images determined by different threshold segmentation methods. The classification accuracies of the iterative method, the OTSU method, the maximum entropy method, and the adaptive threshold segmentation method are, respectively, 85%, 87.5%, 95%, and 97.5%. The adaptive threshold segmentation method proposed in this paper has the highest classification accuracy. Through verification and comparison, the proposed algorithm can segment defects quickly and accurately and suppress noise interference effectively. It is better than other traditional image threshold segmentation methods, validated by both segmentation accuracy and computational efficiency. At the same time, the real-time performance of our algorithm was performed on the advanced SEED-DVS8168 platform.

Unsupervised Semantic Segmentation of PolSAR Images Based on Multiview Similarity

Unsupervised Semantic Segmentation of PolSAR Images Based on Multiview Similarity

Q-Seg: Quantum Annealing-Based Unsupervised Image Segmentation.

We present Q-Seg, a novel unsupervised image segmentation method based on quantum annealing, tailored for existing quantum hardware. We formulate the pixel- wise segmentation problem, which assimilates spectral and spatial information of the image, as a graph-cut optimization task. Our method efficiently leverages the interconnected qubit topology of the D-Wave Advantage device, offering superior scalability over existing quantum approaches and outperforming several tested state-of-the-art classical methods. Empirical evaluations on synthetic datasets have shown that Q-Seg has better runtime performance than the state-of-the-art classical optimizer Gurobi. The method has also been tested on earth observation image segmentation, a critical area with noisy and unreliable annotations. In the era of noisy intermediate-scale quantum, Q-Seg emerges as a reliable contender for real-world applications in comparison to advanced techniques like Segment Anything. Consequently, Q-Seg offers a promising solution using available quantum hardware, especially in situations constrained by limited labeled data and the need for efficient computational runtime.

Retina image segmentation using the three-path Unet model

Unsupervised image segmentation is a technique that divides an image into distinct regions or objects without prior labeling. This approach offers flexibility and adaptability to various types of image data. Particularly for large datasets, it eliminates the need for manual labeling, thereby it presents advantages in terms of time and labor costs. However, when applied to retinal image segmentation, challenges arise due to variations in data, presence of noise, and manual threshold adjustments, which can lead to over-segmentation or under-segmentation of small blood vessel boundaries and endpoints. In order to enhance the precision and accuracy of retinal image segmentation, we propose a novel image supervised segmentation network based on three-path Unet model.Firstly, the Haar wavelet transform is employed to extract high-frequency image information, which forms the foundation for the proposed HaarNet, a Unet-inspired architecture. Next, the HaarNet is integrated with the Unet and SegNet frameworks to develop a three-path Unet model, referred to as TP-Unet. Finally, the model is further refined into TP-Unet+AE+DSL by incorporating the advantages of auto-encoding (AE) and deep supervised learning (DSL) techniques, thereby enhancing the overall performance of the system. To evaluate the effectiveness of our proposed model, we conduct experiments using the DRIVE and CHASE public datasets. On the DRIVE dataset, our recommended model achieves a Dice coefficient of 0.8291 and a sensitivity index of 0.8184. These results significantly outperform the Unet model by 1.34%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1.34\\%$$\\end{document} and 2.60%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2.60\\%$$\\end{document}, respectively. Furthermore, our model demonstrates excellent performance on the CHASE dataset, with a Dice coefficient of 0.8162, a sensitivity of 0.8242, and an accuracy of 0.9664. These metrics surpass the Unet model by 3.20%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3.20\\%$$\\end{document}, 6.66%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$6.66\\%$$\\end{document}, and 0.42%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.42\\%$$\\end{document}, respectively. Our proposed model provides more accurate and reliable results for retinal vessel segmentation, which holds significant potential for assisting doctors in their diagnosis.

Combining Color and Spatial Image Features for Unsupervised Image Segmentation with Mixture Modelling and Spectral Clustering

The demand for accurate and reliable unsupervised image segmentation methods is high. Regardless of whether we are faced with a problem for which we do not have a usable training dataset, or whether it is not possible to obtain one, we still need to be able to extract the desired information from images. In such cases, we are usually gently pushed towards the best possible clustering method, as it is often more robust than simple traditional image processing methods. We investigate the usefulness of combining two clustering methods for unsupervised image segmentation. We use the mixture models to extract the color and spatial image features based on the obtained output segments. Then we construct a similarity matrix (adjacency matrix) based on these features to perform spectral clustering. In between, we propose a label noise correction using Markov random fields. We investigate the usefulness of our method on many hand-crafted images of different objects with different shapes, colorization, and noise. Compared to other clustering methods, our proposal performs better, with 10% higher accuracy. Compared to state-of-the-art supervised image segmentation methods based on deep convolutional neural networks, our proposal proves to be competitive.

Pixel-level clustering network for unsupervised image segmentation

While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level for training is nearly impossible. Therefore, the study of unsupervised image segmentation methods is essential. In this paper, we present a pixel-level clustering framework for segmenting images into regions without using ground truth annotations. The proposed framework includes feature embedding modules with an attention mechanism, a feature statistics computing module, image reconstruction, and superpixel segmentation to achieve accurate unsupervised segmentation. Additionally, we propose a training strategy that utilizes intra-consistency within each superpixel, inter-similarity/dissimilarity between neighboring superpixels, and structural similarity between images. To avoid potential over-segmentation caused by superpixel-based losses, we also propose a post-processing method. Furthermore, we present an extension of the proposed method for unsupervised semantic segmentation. We conducted experiments on three publicly available datasets (Berkeley segmentation dataset, PASCAL VOC 2012 dataset, and COCO-Stuff dataset) to demonstrate the effectiveness of the proposed framework. The experimental results show that the proposed framework outperforms previous state-of-the-art methods.

Image segmentation and dominant region feature extraction for original soil: Towards soil property prediction based on images acquired from smartphones

Prediction of soil properties based on images of original soil acquired from smartphones is considered a potential alternative to conventional soil property determination due to its convenience and low cost. However, images of the original soil may contain distracting information such as fissures, shadows, and rocks, which may affect the image feature extraction and property prediction results. Four unsupervised image segmentation methods, namely the maximum interclass variance (OUST) method, the local adaptive threshold segmentation (LATS) method, the K-means clustering segmentation (KMCS) method, and the natural break point segmentation (NBPS) method, were used to segment 62 images of original soil taken by smartphones in outdoor sunny conditions. The number of segmentation levels (N) for KMCS and NBPS varied from 2 to 10. The dominant region, determined as the region with the highest percentage of image area after segmentation, was selected for subsequent property prediction. The results of the segmentation methods revealed significant differences in the dominant regions, leading to significant variations in color and texture features (p < 0.05). The random forest approach was used to construct predictive models for soil Munsell colour, soil organic matter (SOM) content, and soil texture content. The validation results demonstrated that the image segmentation methods improved the prediction accuracy of all three soil properties compared to that of the unsegmented images. Among the segmentation methods, KMCS (N = 3 and 4) exhibited the highest segmentation performance, surpassing the widely used OUST method. This research highlights the significance of image segmentation methods in predicting soil properties based on images of original soil samples and recommended it as an essential process for future soil image processing. The findings of this study have the potential to advance the development of smartphone-based prediction of properties of original soils.

Unsupervised leaf segmentation in complex backgrounds using mutual information minimization

Leaf segmentation is crucial for plant recognition, especially for tree species identification. In natural environments, leaf segmentation can be very challenging due to the lack of prior information about leaves and the variability of backgrounds. In typical applications, supervised algorithms often require pixel-level annotation of regions, which can be labour-intensive and limited to identifying plant species using pre-labelled samples. On the other hand, traditional unsupervised image segmentation algorithms require specialised parameter tuning for leaf images to achieve optimal results. Therefore, this paper proposes an unsupervised leaf segmentation method that combines mutual information with neural networks to better generalise to unknown samples and adapt to variations in leaf shape and appearance to distinguish and identify different tree species. First, a model combining a Variational Autoencoder (VAE) and a segmentation network is used as a pre-segmenter to obtain dynamic masks. Secondly, the dynamic masks are combined with the segmentation masks generated by the mask generator module to construct the initial mask. Then, the patcher module uses the Mutual Information Minimum (MIM) loss as an optimisation objective to reconstruct independent regions based on this initial mask. The process of obtaining dynamic masks through pre-segmentation is unsupervised, and the entire experimental process does not involve any label information. The experimental method was performed on tree leaf images with a naturally complex background using the publicly available Pl@ntLeaves dataset. The results of the experiment showed that compared to existing excellent methods on this dataset, the IoU (Intersection over Union) index increased by 3.9%.

Unsupervised statistical image segmentation using bi-dimensional hidden Markov chains model with application to mammography images

Hidden Markov chain (HMC) models have been widely used in unsupervised image segmentation. In these models, there is a double process; a hidden one noted X and an observed one, which is often one-dimensional, noted Y. The latter is constituted by pixels of a noisy image after transforming its bi-dimensional form into a mono-dimensional sequence. In this context, these models run into a problem of relationships between pixels which is often solved by applying curves such as the Hilbert-Peano scan when modeling the image under study. We propose enriching the HMC model by introducing a second component to the observed process Y based on the average of two observations which are neighbors in the image but are not in the chain of each considered pixel. This gives a bi-dimensional HMC model which has the same structure as the classical model except for the two-dimensional case of the low modeling noise. The estimation of the parameters of this model is carried out by using a three-algorithm approach: Bayesian one based mainly on the Markov Chain Monte Carlo (MCMC) methods, Expectation–Maximization (EM), and Iterative Conditional Estimation (ICE). We apply the final Bayesian decision criteria Marginal Posterior Mode to come up with a final configuration of the result X. The proposed model is compared to the classical HMC model in combination with the Hilbert-Peano scan numerically through simulated data and visually through synthetic and mammogram images.

In vitro laser scanning confocal microscopy and unsupervised segmentation: Quantification of cytosolic calcium and RNA distribution in hypoxic neurons.

The mimicry of neurodegenerative diseases in vitro can be observed through the induction of chronic hypoxia, and the impact of this stress is monitored using multiplexed imaging techniques. While laser scanning confocal microscopy (LSCM) is a valuable tool for observing single neurons under degenerative conditions, accurately quantifying RNA distribution and cell size by deep learning tools remains challenging due to the lack of annotated training datasets. To address this, we propose a framework that combines 3D tracking of RNA distribution and cell size identification using unsupervised image segmentation. Additionally, we quantified the calcium level in neurons using fluorescent microscopy using unsupervised image segmentation. First, we performed imaging of neuronal morphology using differential interference contrast (DIC) optics and RNA/calcium level imaging using fluorescent microscopy. Next, we performed k-means clustering-based cell segmentation. The results show that our framework can distinguish between distinct neuronal states under control and chronic hypoxic conditions. The analysis reveals that hypoxia induces a significant increase in cytosolic calcium level, reduction in neuron diameter, and alterations in RNA distribution.Clinical Relevance- The proposed framework is crucial to study the neurodegeneration process and evaluating the efficacy of neuroprotective drugs through image analysis.

Unsupervised image segmentation with robust virtual class contrast

Unsupervised Image Segmentation (UIS) is a challenging problem in computer vision that aims to classify pixels in an image into different semantic classes without using any labels. Among the various UIS methods, MaskContrast performs well when dealing with complex objects containing lots of detail. It utilizes prior knowledge from a pretrained saliency detection model to identify foreground pixels and leverages contrastive learning to learn the representations of those foreground pixels. However, this method is not designed to handle situations where foreground pixels belong to multiple semantic classes. To mitigate this problem, we propose a novel method for UIS called Robust Virtual Class Contrast (RVCC), which characterizes foreground pixels based on their “virtual classes” rather than just saliency masks. A virtual class can be viewed as the representation of some unknown object in the training data. Our method employs K-means clustering to find the pseudo virtual class label for every foreground pixel at the start of each training epoch. These pseudo-labels are then used to guide the learning of pixel representations. Additionally, to avoid the overconfidence of pseudo-label prediction, RVCC incorporates an additional regularization term that encourages consistency between the predictions under weak and strong augmentations. Our experiments demonstrate that RVCC outperforms existing baselines on the Pascal VOC2012 and MSRCv2 datasets, showcasing its capability for the UIS problem.