Related papers: Towards Effective Image Forensics via A Novel Comp…

Despite recent progress in splicing detection, deep learning-based forensic tools remain difficult to deploy in practice due to their high sensitivity to training conditions. Even mild post-processing applied to evaluation images can…

This paper proposes a novel communication-efficient split learning (SL) framework, named SplitFC, which reduces the communication overhead required for transmitting intermediate feature and gradient vectors during the SL training process.…

The proliferation of sophisticated image editing tools and generative artificial intelligence models has made verifying the authenticity of digital images increasingly challenging, with important implications for journalism, forensic…

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies…

Salient object detection increasingly receives attention as an important component or step in several pattern recognition and image processing tasks. Although a variety of powerful saliency models have been intensively proposed, they…

Although deep neural networks have been a dominant method for many 2D vision tasks, it is still challenging to apply them to 3D tasks, such as medical image segmentation, due to the limited amount of annotated 3D data and limited…

The recent advances in Deep Neural Networks (DNNs) stem from their exceptional performance across various domains. However, their inherent large size hinders deploying these networks on resource-constrained devices like edge, mobile, and…

Skeletonization extracts thin representations from images that compactly encode their geometry and topology. These representations have become an important topological prior for preserving connectivity in curvilinear structures, aiding…

Incorporating semantic information into the codecs during image compression can significantly reduce the repetitive computation of fundamental semantic analysis (such as object recognition) in client-side applications. The same practice…

This paper proposes a novel method for high-quality image segmentation of both objects and scenes. Inspired by the dilation and erosion operations in morphological image processing techniques, the pixel-level image segmentation problems are…

The inclusion of spatial information into spectral classifiers for fine-resolution hyperspectral imagery has led to significant improvements in terms of classification performance. The task of spectral-spatial hyperspectral image…

Robust local feature representations are essential for spatial intelligence tasks such as robot navigation and augmented reality. Establishing reliable correspondences requires descriptors that provide both high discriminative power and…

Subspace clustering has become widely adopted for the unsupervised analysis of hyperspectral images (HSIs). Recent model-aware deep subspace clustering methods often use a two-stage framework, involving the calculation of a…

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

Change detection, i.e. identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of…

The use of brain images as markers for diseases or behavioral differences is challenged by the small effects size and the ensuing lack of power, an issue that has incited researchers to rely more systematically on large cohorts. Coupled…

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…

Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference. However, their practical runtime usually lags behind the theoretical…

It is known that JPEG images uploaded to social networks (SNs) are mostly re-compressed by the social network providers. Because of such a situation, a new image identification scheme for double-compressed JPEG images is proposed in this…

In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in…