Related papers: Instance camera focus prediction for crystal agglo…
A standard method to study the mass distribution in galaxy clusters is through strong lensing of background galaxies in which the positions of multiple images of the same source constrain the surface mass distribution of the cluster.…
Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-based methods have high…
Image segmentation as a clustering problem is to identify pixel groups on an image without any preliminary labels available. It remains a challenge in machine vision because of the variations in size and shape of image segments.…
We consider the problem of amodal instance segmentation, the objective of which is to predict the region encompassing both visible and occluded parts of each object. Thus far, the lack of publicly available amodal segmentation annotations…
A routine crystallography technique, crystal structure analysis, is rarely performed in computational condensed matter research. The lack of methods to identify and characterize crystal structures reliably in particle simulation data…
Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and…
A conditional random field (CRF) model for cloud detection in ground based sky images is presented. We show that very high cloud detection accuracy can be achieved by combining a discriminative classifier and a higher order clique potential…
Fine-grained visual categorization is a classification task for distinguishing categories with high intra-class and small inter-class variance. While global approaches aim at using the whole image for performing the classification,…
The proposed method extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts. A fully convolutional network is trained to produce consistent pixel-level embedding…
High-throughput 2D and 3D scanning electron microscopy, which relies on automation and dependable control algorithms, requires high image quality with minimal human intervention. Classical focus and astigmatism correction algorithms attempt…
Instance-level alignment is widely exploited for person re-identification, e.g. spatial alignment, latent semantic alignment and triplet alignment. This paper probes another feature alignment modality, namely cluster-level feature alignment…
Image segmentation is a fundamental task in computer vision. Data annotation for training supervised methods can be labor-intensive, motivating unsupervised methods. Current approaches often rely on extracting deep features from pre-trained…
Dataset condensation aims to condense a large dataset with a lot of training samples into a small set. Previous methods usually condense the dataset into the pixels format. However, it suffers from slow optimization speed and large number…
Finding a suitable data representation for a specific task has been shown to be crucial in many applications. The success of subspace clustering depends on the assumption that the data can be separated into different subspaces. However,…
Statistically sound crystallographic symmetry classifications are obtained with information theory based methods in the presence of approximately Gaussian distributed noise. A set of three synthetic images with very strong Fedorov type…
Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks. However, none of the existing methods is able to identify object instances in the detected salient regions. In this paper, we present…
This review presents various image segmentation methods using complex networks. Image segmentation is one of the important steps in image analysis as it helps analyze and understand complex images. At first, it has been tried to classify…
We describe an objective and automated method for detecting clusters of galaxies from optical imaging data. This method is a variant of the so-called `matched-filter' technique pioneered by Postman et al. (1996). With simultaneous use of…
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure. One is to predict pixel…
In order to identify clusters of objects with features transformed by unknown affine transformations, we develop a Bayesian cluster process which is invariant with respect to certain linear transformations of the feature space and able to…