In this systematic literature review, we present a comprehensive review of the state-of-the-art approaches reported in carcinoma diagnosis using histopathological images.
While most existing deep learning research focused on medical images in a supervised way, we introduce an unsupervised method for the detection of intracranial aneurysms based on 3D point cloud data.
As a popular representation of 3D data, point cloud may contain noise and need to be filtered before use.
It consists of two phases: (a) feature encoding which learns representations of local patches, and (b) normal estimation that takes the learned representation as input and regresses the normal vector.
Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training.
In this paper, we propose a novel and fully end-to-end trainable approach, called regional contrastive consistency regularization (RCCR) for domain adaptive semantic segmentation.
In this paper, we focus on a fundamental and practical research problem: judging whether a point cloud is plagiarized or copied to another point cloud in the presence of several manipulations (e. g., similarity transformation, smoothing).
This security model automatically assesses the security of the IoT network by capturing potential attack paths.
Extensive experiments demonstrate that our method can soundly boost the performance on both cross-domain object detection and segmentation for state-of-the-art techniques.
In this paper, we study a practical setting called Specific Domain Adaptation (SDA) that aligns the source and target domains in a demanded-specific dimension.
The generated contextual mask is critical in this work and will guide the domain mixup.
Specifically, by partitioning the template image into several regions and measuring the similarity of each region independently, multiple objectives are built and deformation estimation can thus be realized by solving the MOP with off-the-shelf multi-objective evolutionary algorithms (MOEAs).
Extensive experiments show that our unsupervised learning method enables comparable detection performance to state-of-the-art supervised techniques, in both the intra- and inter-dataset settings.
In this paper, we identify two main bottlenecks: (1) the lack of a publicly available imaging dataset for diverse species of nematodes (especially the species only found in natural environment) which requires considerable human resources in field work and experts in taxonomy, and (2) the lack of a standard benchmark of state-of-the-art deep learning techniques on this dataset which demands the discipline background in computer science.
Current annotation for plant disease images depends on manual sorting and handcrafted features by agricultural experts, which is time-consuming and labour-intensive.
It has become increasingly challenging to distinguish real faces from their visually realistic fake counterparts, due to the great advances of deep learning based face manipulation techniques in recent years.
In particular, we relate the transferred image with the example image under the Gaussian Mixture Model (GMM) and regard the transferred image color as the GMM centroids.
In this paper, we propose to use hybrid features in addition to foreground and background features to represent scene images.
Existing research in scene image classification has focused on either content features (e. g., visual information) or context features (e. g., annotations).
To capture the underlying structure of live faces data in latent representation space, we propose to train the live face data only, with a convolutional Encoder-Decoder network acting as a Generator.
In this paper, we propose a novel feature-preserving normal estimation method for point cloud filtering with preserving geometric features.
Guided by this mask, we propose a ClassOut strategy to realize effective regional consistency in a fine-grained manner.
Instead, leveraging inter-model disagreement between different models is a key to locate pseudo label errors.
In evolutionary algorithms, genetic operators iteratively generate new offspring which constitute a potentially valuable set of search history.
In this paper, we propose a novel type of features -- hybrid deep features, for scene images.
In this paper, we propose a novel deep learning approach that automatically and robustly filters point clouds with removing noise and preserving sharp features and geometric details.
The WA data can be naturally obtained in an interactive way for specific tasks, for example, in the case of homography estimation, one can easily annotate points on the same plane/object with a single label by observing the image.
Sharing images online poses security threats to a wide range of users due to the unawareness of privacy information.
In this paper, we introduce novel semantic features of an image based on the annotations and descriptions of its similar images available on the web.
Instead of using an intermediate estimated guidance, we propose to explicitly transfer facial expression by directly mapping two unpaired input images to two synthesized images with swapped expressions.
Nevertheless, most of the existing feature extraction methods, which extract features based on pixels, color, shape/object parts or objects on images, suffer from limited capabilities in describing semantic information (e. g., object association).
This paper presents a simple yet effective method for feature-preserving surface smoothing.
Computational Geometry Graphics
We propose a novel genetic algorithm to solve the image deformation estimation problem by preserving the genetic diversity.
Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images.
Due to the combination of source AU-related information and target AU-free information, the latent feature domain with transferred source label can be learned by maximizing the target-domain AU detection performance.
To settle this issue, we propose a blur-countering method for detecting valid keypoints for various types and degrees of blurred images.