We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image pixels into foreground and background, with the goal of minimizing predictability of one set from the other. An easily computed loss drives a greedy search process to maximize inpainting error over these partitions. Our method does not involve training deep networks, is computationally cheap, class-agnostic, and even applicable in isolation to a single unlabeled image. Experiments demonstrate that it achieves a new state-of-the-art in unsupervised segmentation quality, while being substantially faster and more general than competing approaches.
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following criteria: (a) pixels of similar features should be assigned the same label, (b) spatially continuous pixels should be assigned the same label, and (c) the number of unique labels should be large. Although these criteria are incompatible, the proposed approach minimizes the combination of similarity loss and spatial continuity loss to find a plausible solution of label assignment that balances the aforementioned criteria well. The contributions of this study are four-fold. First, we propose a novel end-to-end network of unsupervised image segmentation that consists of normalization and an argmax function for differentiable clustering. Second, we introduce a spatial continuity loss function that mitigates the limitations of fixed segment boundaries possessed by previous work. Third, we present an extension of the proposed method for segmentation with scribbles as user input, which showed better accuracy than existing methods while maintaining efficiency. Finally, we introduce another extension of the proposed method: unseen image segmentation by using networks pre-trained with a few reference images without re-training the networks. The effectiveness of the proposed approach was examined on several benchmark datasets of image segmentation.
In this work, we propose a new unsupervised image segmentation approach based on mutual information maximization between different constructed views of the inputs. Taking inspiration from autoregressive generative models that predict the current pixel from past pixels in a raster-scan ordering created with masked convolutions, we propose to use different orderings over the inputs using various forms of masked convolutions to construct different views of the data. For a given input, the model produces a pair of predictions with two valid orderings, and is then trained to maximize the mutual information between the two outputs. These outputs can either be low-dimensional features for representation learning or output clusters corresponding to semantic labels for clustering. While masked convolutions are used during training, in inference, no masking is applied and we fall back to the standard convolution where the model has access to the full input. The proposed method outperforms current state-of-the-art on unsupervised image segmentation. It is simple and easy to implement, and can be extended to other visual tasks and integrated seamlessly into existing unsupervised learning methods requiring different views of the data.
Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet and IODINE, decompose scenes into objects in an unsupervised fashion. Their underlying generative processes, however, do not account for component interactions. Hence, neither of them allows for principled sampling of novel scenes. Here we present GENESIS, the first object-centric generative model of 3D visual scenes capable of both decomposing and generating scenes by capturing relationships between scene components. GENESIS parameterises a spatial GMM over images which is decoded from a set of object-centric latent variables that are either inferred sequentially in an amortised fashion or sampled from an autoregressive prior. We train GENESIS on several publicly available datasets and evaluate its performance on scene generation, decomposition, and semi-supervised learning.
Probabilistic finite mixture models are widely used for unsupervised clustering. These models can often be improved by adapting them to the topology of the data. For instance, in order to classify spatially adjacent data points similarly, it is common to introduce a Laplacian constraint on the posterior probability that each data point belongs to a class. Alternatively, the mixing probabilities can be treated as free parameters, while assuming Gauss-Markov or more complex priors to regularize those mixing probabilities. However, these approaches are constrained by the shape of the prior and often lead to complicated or intractable inference. Here, we propose a new parametrization of the Dirichlet distribution to flexibly regularize the mixing probabilities of over-parametrized mixture distributions. Using the Expectation-Maximization algorithm, we show that our approach allows us to define any linear update rule for the mixing probabilities, including spatial smoothing regularization as a special case. We then show that this flexible design can be extended to share class information between multiple mixture models. We apply our algorithm to artificial and natural image segmentation tasks, and we provide quantitative and qualitative comparison of the performance of Gaussian and Student-t mixtures on the Berkeley Segmentation Dataset. We also demonstrate how to propagate class information across the layers of deep convolutional neural networks in a probabilistically optimal way, suggesting a new interpretation for feedback signals in biological visual systems. Our flexible approach can be easily generalized to adapt probabilistic mixture models to arbitrary data topologies.
Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes. However, developments on hyperspectral imaging systems enable us to obtain redundant spectral information of the observed scenes from the reflected light source from objects. A few studies using low-level features on hyperspectral images demonstrated that salient object detection can be achieved. In this work, we proposed a salient object detection model on hyperspectral images by applying manifold ranking (MR) on self-supervised Convolutional Neural Network (CNN) features (high-level features) from unsupervised image segmentation task. Self-supervision of CNN continues until clustering loss or saliency maps converges to a defined error between each iteration. Finally, saliency estimations is done as the saliency map at last iteration when the self-supervision procedure terminates with convergence. Experimental evaluations demonstrated that proposed saliency detection algorithm on hyperspectral images is outperforming state-of-the-arts hyperspectral saliency models including the original MR based saliency model.
Advances in the image-based diagnostics of complex biological and manufacturing processes have brought unsupervised image segmentation to the forefront of enabling automated, on the fly decision making. However, most existing unsupervised segmentation approaches are either computationally complex or require manual parameter selection (e.g., flow capacities in max-flow/min-cut segmentation). In this work, we present a fully unsupervised segmentation approach using a continuous max-flow formulation over the image domain while optimally estimating the flow parameters from the image characteristics. More specifically, we show that the maximum a posteriori estimate of the image labels can be formulated as a continuous max-flow problem given the flow capacities are known. The flow capacities are then iteratively obtained by employing a novel Markov random field prior over the image domain. We present theoretical results to establish the posterior consistency of the flow capacities. We compare the performance of our approach on two real-world case studies including brain tumor image segmentation and defect identification in additively manufactured components using electron microscopic images. Comparative results with several state-of-the-art supervised as well as unsupervised methods suggest that the present method performs statistically similar to the supervised methods, but results in more than 90% improvement in the Dice score when compared to the state-of-the-art unsupervised methods.
Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled videos can be collected at relatively low cost. In this paper, we address the unsupervised learning problem in the context of detecting the main foreground objects in single images. We train a student deep network to predict the output of a teacher pathway that performs unsupervised object discovery in videos or large image collections. Our approach is different from published methods on unsupervised object discovery. We move the unsupervised learning phase during training time, then at test time we apply the standard feed-forward processing along the student pathway. This strategy has the benefit of allowing increased generalization possibilities during training, while remaining fast at testing. Our unsupervised learning algorithm can run over several generations of student-teacher training. Thus, a group of student networks trained in the first generation collectively create the teacher at the next generation. In experiments our method achieves top results on three current datasets for object discovery in video, unsupervised image segmentation and saliency detection. At test time the proposed system is fast, being one to two orders of magnitude faster than published unsupervised methods.
Today Bayesian networks are more used in many areas of decision support and image processing. In this way, our proposed approach uses Bayesian Network to modelize the segmented image quality. This quality is calculated on a set of attributes that represent local evaluation measures. The idea is to have these local levels chosen in a way to be intersected into them to keep the overall appearance of segmentation. The approach operates in two phases: the first phase is to make an over-segmentation which gives superpixels card. In the second phase, we model the superpixels by a Bayesian Network. To find the segmented image with the best overall quality we used two approximate inference methods, the first using ICM algorithm which is widely used in Markov Models and a second is a recursive method called algorithm of model decomposition based on max-product algorithm which is very popular in the recent works of image segmentation. For our model, we have shown that the composition of these two algorithms leads to good segmentation performance.
Unsupervised image segmentation aims at clustering the set of pixels of an image into spatially homogeneous regions. We introduce here a class of Bayesian nonparametric models to address this problem. These models are based on a combination of a Potts-like spatial smoothness component and a prior on partitions which is used to control both the number and size of clusters. This class of models is flexible enough to include the standard Potts model and the more recent Potts-Dirichlet Process model \cite{Orbanz2008}. More importantly, any prior on partitions can be introduced to control the global clustering structure so that it is possible to penalize small or large clusters if necessary. Bayesian computation is carried out using an original generalized Swendsen-Wang algorithm. Experiments demonstrate that our method is competitive in terms of RAND\ index compared to popular image segmentation methods, such as mean-shift, and recent alternative Bayesian nonparametric models.
We propose a novel unsupervised image segmentation algorithm, which aims to segment an image into several coherent parts. It requires no user input, no supervised learning phase and assumes an unknown number of segments. It achieves this by first over-segmenting the image into several hundred superpixels. These are iteratively joined on the basis of a discriminative classifier trained on color and texture information obtained from each superpixel. The output of the classifier is regularized by a Markov random field that lends more influence to neighbouring superpixels that are more similar. In each iteration, similar superpixels fall under the same label, until only a few coherent regions remain in the image. The algorithm was tested on a standard evaluation data set, where it performs on par with state-of-the-art algorithms in term of precision and greatly outperforms the state of the art by reducing the oversegmentation of the object of interest.
Color image segmentation is a crucial step in many computer vision and pattern recognition applications. This article introduces an adaptive and unsupervised clustering approach based on Voronoi regions, which can be applied to solve the color image segmentation problem. The proposed method performs region splitting and merging within Voronoi regions of the Dirichlet Tessellated image (also called a Voronoi diagram) , which improves the efficiency and the accuracy of the number of clusters and cluster centroids estimation process. Furthermore, the proposed method uses cluster centroid proximity to merge proximal clusters in order to find the final number of clusters and cluster centroids. In contrast to the existing adaptive unsupervised cluster-based image segmentation algorithms, the proposed method uses K-means clustering algorithm in place of the Fuzzy C-means algorithm to find the final segmented image. The proposed method was evaluated on three different unsupervised image segmentation evaluation benchmarks and its results were compared with two other adaptive unsupervised cluster-based image segmentation algorithms. The experimental results reported in this article confirm that the proposed method outperforms the existing algorithms in terms of the quality of image segmentation results. Also, the proposed method results in the lowest average execution time per image compared to the existing methods reported in this article.
Motivated by a $2$-dimensional (unsupervised) image segmentation task whereby local regions of pixels are clustered via edge detection methods, a more general probabilistic mathematical framework is devised. Critical thresholds are calculated that indicate strong correlation between randomly-generated, high dimensional data points that have been projected into structures in a partition of a bounded, $2$-dimensional area, of which, an image is a special case. A neighbor concept for structures in the partition is defined and a critical radius is uncovered. Measured from a central structure in localized regions of the partition, the radius indicates strong, long and short range correlation in the count of occupied structures. The size of a short interval of radii is estimated upon which the transition from short-to-long range correlation is virtually assured, which defines a demarcation of when an image ceases to be "interesting".
Unsupervised image segmentation algorithms aim at identifying disjoint homogeneous regions in an image, and have been subject to considerable attention in the machine vision community. In this paper, a popular theoretical model with it's origins in statistical physics and social dynamics, known as the Deffuant-Weisbuch model, is applied to the image segmentation problem. The Deffuant-Weisbuch model has been found to be useful in modelling the evolution of a closed system of interacting agents characterised by their opinions or beliefs, leading to the formation of clusters of agents who share a similar opinion or belief at steady state. In the context of image segmentation, this paper considers a pixel as an agent and it's colour property as it's opinion, with opinion updates as per the Deffuant-Weisbuch model. Apart from applying the basic model to image segmentation, this paper incorporates adjacency and neighbourhood information in the model, which factors in the local similarity and smoothness properties of images. Convergence is reached when the number of unique pixel opinions, i.e., the number of colour centres, matches the pre-specified number of clusters. Experiments are performed on a set of images from the Berkeley Image Segmentation Dataset and the results are analysed both qualitatively and quantitatively, which indicate that this simple and intuitive method is promising for image segmentation. To the best of the knowledge of the author, this is the first work where a theoretical model from statistical physics and social dynamics has been successfully applied to image processing.
While significant attention has been recently focused on designing supervised deep semantic segmentation algorithms for vision tasks, there are many domains in which sufficient supervised pixel-level labels are difficult to obtain. In this paper, we revisit the problem of purely unsupervised image segmentation and propose a novel deep architecture for this problem. We borrow recent ideas from supervised semantic segmentation methods, in particular by concatenating two fully convolutional networks together into an autoencoder--one for encoding and one for decoding. The encoding layer produces a k-way pixelwise prediction, and both the reconstruction error of the autoencoder as well as the normalized cut produced by the encoder are jointly minimized during training. When combined with suitable postprocessing involving conditional random field smoothing and hierarchical segmentation, our resulting algorithm achieves impressive results on the benchmark Berkeley Segmentation Data Set, outperforming a number of competing methods.
Unsupervised image segmentation and denoising are two fundamental tasks in image processing. Usually, graph based models such as multicut are used for segmentation and variational models are employed for denoising. Our approach addresses both problems at the same time. We propose a novel ILP formulation of the first derivative Potts model with the $\ell_1$ data term, where binary variables are introduced to deal with the $\ell_0$ norm of the regularization term. The ILP is then solved by a standard off-the-shelf MIP solver. Numerical experiments are compared with the multicut problem.