Aerial Image Segmentation with Clustering Using Fireworks Algorithm

Image segmentation by fusion of low level and domain specific information via Markov Random Fields

Conventional unsupervised image segmentation methods return many superpixels or object parts and thus tend to over-segmentation. In this paper, we present a novel post-processing approach for unsupervised object-level image segmentation (UnOLIS). Starting with the results of any conventional unsupervised segmentation method, we first combine a global region-based saliency and a robust background feature to cluster the pre-segmented regions into foreground and background. We then design a region growing process, encoded with several object priors, to generate a high quality foreground object segmentation. In parallel, we group the background regions into different stuffs by clustering. We test our method on the Berkeley Segmentation Dataset (BSDS500). Our approach significantly improves conventional unsupervised segmentation methods and achieves almost comparable results as the state-of-the-art supervised image segmentation methods.

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

This paper proposes a Markov random field (MRF) model-based method for unsupervised segmentation of images consisting of multiple textures. This method uses a hierarchical MRF with two layers, the first layer representing an unobservable region image and the second layer representing multiple textures which cover each region. This method is an iterative method based on the framework of the expectation and maximization (EM) method. We make use of an approximation for the Baum function in the expectation step. This reduces the parameter estimation to the maximum likelihood (ML) estimation given the current estimate of the region image. An estimation of the region image (image segmentation) is carried out by a deterministic relaxation method proposed by us.

Unsupervised image segmentation methods typically assume zero a-priori knowledge about the data semantics. This assumption does hold in many practical scenarios where, although the training data might not be annotated, the target semantic image region classes are known. In these settings, text-driven prompting methods for semantic image segmentation offer noticeable improvement in segmentation accuracy over purely unsupervised approaches. However, such approaches are still limited by: a) inherent text-prompt semantic ambiguity, b) ineffective adaptation to target domain distributions, and c) excessive computational and architectural complexity. To address these shortcomings, we propose the Multiclass Extreme Weak Supervision (MEWS) framework for semantic image segmentation. MEWS assumes the availability of extremely few class-based pixel-level image annotations, e.g., few annotated image pixels per class in very few training images. Such pixel-based image prompts are thereby employed to form image region class prototypes. They can be used to leverage low-complexity unsupervised image segmentation architectures to be trained by our novel prototype-based triplet loss that learns discriminative image features by promoting intra-class image feature compactness while enforcing inter-class feature vector separation. Consequently, the proposed MEWS image segmentation architecture leads to increased weakly supervised training efficiency, bridging the performance gap between supervised and unsupervised image segmentation methods. Our experimental results indicate that the proposed methods compare favorably against text-based prompting image segmentation methods. It yields superior image segmentation accuracy in publicly available image segmentation datasets (e.g., Cityscapes), as well as in Natural Disaster Management (NDM) ones. • A novel Multiclass Extreme Weakly Supervised (MEWS) semantic segmentation framework is proposed that generalizes the original binary EWS DNN architecture by utilizing only sparse, per-class, few-pixel per class labelling. • A class prototype-based triplet loss function is designed that pulls same-class prototype feature vectors together, while pushing mean prototype feature vectors belonging to different classes apart. • A multiclass dynamic thresholding mechanism improves contrastive learning, without additional supervision or manual hyperparameter tuning. • MEWS segmentation excels in accuracy, scaling with annotation, ablation study on loss, validated on NDM Sardinia Wildfire dataset.

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}

Conventional unsupervised image segmentation methods use color and geometric information and apply clustering algorithms over pixels. They preserve object boundaries well but often suffer from over-segmentation due to noise and artifacts in the images. In this paper, we contribute on a preprocessing step for image smoothing, which alleviates the burden of conventional unsupervised image segmentation and enhance their performance. Our approach relies on a convolutional autoencoder (CAE) with the total variation loss (TVL) for unsupervised learning. We show that, after our CAE-TVL preprocessing step, the over-segmentation effect is significantly reduced using the same unsupervised image segmentation methods. We evaluate our approach using the BSDS500 image segmentation benchmark dataset and show the performance enhancement introduced by our approach in terms of both increased segmentation accuracy and reduced computation time. We examine the robustness of the trained CAE and show that it is directly applicable to other natural scene images.

Heterogeneous image segmentation is one of the most important tasks in image processing. It consists in partitioning the image into a set of disjoint regions. In this paper, we propose a new unsupervised image segmentation method that we call Unsupervised Image Segmentation (UIS). Our proposal performs an efficient image partition efficiently into primitive regions. This process is ensured by a local adaptive Kmeans and a novel centroids initialization. Then, similar sets are agglomerated to form homogeneous regions. For that, a low-level feature merging is employed according to a hierarchical linkage approach. Finally, in case of over-segmentation, appearing outlier regions are removed using a post process stage. Therefore, the UIS method allows to determine automatically the image region number. Indeed, it extends the Kmeans clustering to obtain meaningful regions. Several experiments were conducted using two heterogeneous image datasets. A comparison with well-known segmentation methods was also performed using the Liu's factor measure.

A Markov Random Field based image segmentation system which combines top-down and bottom-up segmentation approaches is proposed in this study. The system is especially proposed for applications where no labeled training set is available, but some priori general information referred as domain specific information about the dataset is available. Domain specific information is received from a domain expert and formalized by a mathematical representation. The type of information and its representation depends on the content of the image dataset to be segmented. This information is integrated to the segmentation process in an unsupervised framework. Due to the inclusion of domain specific information, this approach can be considered as a first step to semantic image segmentation under an unsupervised MRF model. The proposed system is compared with the state of the art unsupervised image segmentation methods quantitatively via two evaluation metrics; consistency error and probabilistic rand index and satisfactory results are obtained.Keywordsimage segmentationMarkov Random Fieldsdomain specific segmentation

In this paper, we present a novel method for unsupervised image segmentation. Image segmentation is cast as a clustering problem, which aims to partition a given set of pixels into a number of homogenous clusters, based on a similarity criterion. The clustering problem is a difficult optimization problem for two main reasons: first the search space of the optimization is too large, second the clustering objective function is typically non convex and thus may exhibit a large number of local minima. Ant Colony Optimization is a recent multi-agent approach based on artificial ants for solving hard combinatorial optimization problems. We propose the use of the Max-Min Ant System (MMAS) to solve the clustering problem in the field of image segmentation. Each pixel within the image is mapped to its closest cluster taking into account its immediate neighborhood. The obtained results are encouraging and prove the feasibility of the proposed algorithm.

Unsupervised brain tumor segmentation using a symmetric-driven adversarial network

This paper presents a novel method for unsupervised image segmentation. The method determines the reasonable segments for final segmentation by exploiting both global and local context cues on multiple segmentation proposals. The proposal is obtained by using any existing segmentation algorithms, providing the diverse segment cues to guide segmentation. An iterative process is used to perform the cues integration and the image segmentation, including the segments modeling and the segments labeling. The former estimates the distribution of shared segments, while the latter labels each proposal into segments by minimizing an energy function. The final segmentation is produced when the consistent spatial layout is found in different proposals. Compared with the existing methods, the segmentation results are more satisfying on the Berkeley Segmentation Database.

One major technique debt in video object segmentation is to label the object masks for training instances. As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue for video object segmentation training. Our method conducts semantic segmentation using instance segmentation networks and, then, selects the segmented object of interest as the pseudo ground truth based on the motion information. Afterwards, the pseudo ground truth is exploited to finetune the pretrained objectness network to facilitate object segmentation in the remaining frames of the video. We show that the pseudo ground truth could effectively improve the segmentation performance. This straightforward unsupervised video object segmentation method is more efficient than existing methods. Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets. And the category-agnostic pseudo ground truth has great potential to extend to multiple arbitrary object tracking.

In synthetic aperture radar (SAR) images, pixel-level Ground Truth (GT) is a scarce resource compared to Bounding Box (BBox) annotations. Therefore, exploring the use of unsupervised instance segmentation methods to convert BBox-level annotations into pixel-level GT holds great significance in the SAR field. However, previous unsupervised segmentation methods fail to perform well on SAR images due to the presence of speckle noise, low imaging accuracy, and gradual pixel transitions at the boundaries between targets and background, resulting in unclear edges. In this paper, we propose a Multi-threshold Adaptive Decision Network (MtAD-Net), which is capable of segmenting SAR ship images under unsupervised conditions and demonstrates good performance. Specifically, we design a Multiple CFAR Threshold-extraction Module (MCTM) to obtain a threshold vector by a false alarm rate vector. A Local U-shape Feature Extractor (LUFE) is designed to project each pixel of SAR images into a high-dimensional feature space, and a Global Vision Transformer Encoder (GVTE) is designed to obtain global features, and then, we use the global features to obtain a probability vector, which is the probability of each CFAR threshold. We further propose a PLC-Loss to adaptively reduce the feature distance of pixels of the same category and increase the feature distance of pixels of different categories. Moreover, we designed a label smoothing module to denoise the result of MtAD-Net. Experimental results on the dataset show that our MtAD-Net outperforms traditional and existing deep learning-based unsupervised segmentation methods in terms of pixel accuracy, kappa coefficient, mean intersection over union, frequency weighted intersection over union, and F1-Score.

Sub-scene segmentation using constraints based on Gestalt principles