Related papers: Colour Constancy: Biologically-inspired Contrast V…

The process of dynamic state estimation (filtering) based on point process observations is in general intractable. Numerical sampling techniques are often practically useful, but lead to limited conceptual insight about optimal…

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…

Pooling is an important component in convolutional neural networks (CNNs) for aggregating features and reducing computational burden. Compared with other components such as convolutional layers and fully connected layers which are…

We consider a variation of the prototype combinatorial-optimisation problem known as graph-colouring. Our optimisation goal is to colour the vertices of a graph with a fixed number of colours, in a way to maximise the number of different…

There is active research targeting local image manipulations that can fool deep neural networks (DNNs) into producing incorrect results. This paper examines a type of global image manipulation that can produce similar adverse effects.…

Copying an element from a photo and pasting it into a painting is a challenging task. Applying photo compositing techniques in this context yields subpar results that look like a collage --- and existing painterly stylization algorithms,…

Recent colorization works implicitly predict the semantic information while learning to colorize black-and-white images. Consequently, the generated color is easier to be overflowed, and the semantic faults are invisible. As a human…

Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found…

Visual-Semantic Embedding (VSE) aims to learn an embedding space where related visual and semantic instances are close to each other. Recent VSE models tend to design complex structures to pool visual and semantic features into fixed-length…

We consider a set of M images, whose pixel intensities at a common point can be treated as the components of a M-dimensional vector. We are interested in the estimation of the modulus of such a vector associated to a compact source. For…

Automatic face recognition has received significant performance improvement by developing specialised facial image representations. On the other hand, generic object recognition has rarely been applied to the face recognition. Spatial…

Aligning partially overlapping point sets where there is no prior information about the value of the transformation is a challenging problem in computer vision. To achieve this goal, we first reduce the objective of the robust point…

Global pooling is one of the most significant operations in many machine learning models and tasks, which works for information fusion and structured data (like sets and graphs) representation. However, without solid mathematical…

Polarization images provide rich physical information that is fundamentally absent from standard RGB images, benefiting a wide range of computer vision applications such as reflection separation and material classification. However, the…

This paper proposes a novel polarization sensor structure and network architecture to obtain a high-quality RGB image and polarization information. Conventional polarization sensors can simultaneously acquire RGB images and polarization…

Performance of deep learning algorithms decreases drastically if the data distributions of the training and testing sets are different. Due to variations in staining protocols, reagent brands, and habits of technicians, color variation in…

Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224x224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this…

Compared with global average pooling in existing deep convolutional neural networks (CNNs), global covariance pooling can capture richer statistics of deep features, having potential for improving representation and generalization abilities…

Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of…

This paper proposes a novel multi-exposure image fusion method based on exposure compensation. Multi-exposure image fusion is a method to produce images without color saturation regions, by using photos with different exposures. However, in…