Related papers: Region Mutual Information Loss for Semantic Segmen…
Estimating mutual information between continuous random variables is often intractable and extremely challenging for high-dimensional data. Recent progress has leveraged neural networks to optimize variational lower bounds on mutual…
There has been significant progress in Masked Image Modeling (MIM). Existing MIM methods can be broadly categorized into two groups based on the reconstruction target: pixel-based and tokenizer-based approaches. The former offers a simpler…
Semantic segmentation consists of assigning a semantic label to each pixel according to predefined classes. This process facilitates the understanding of object appearance and spatial relationships, playing an important role in the global…
Sliced mutual information (SMI) is defined as an average of mutual information (MI) terms between one-dimensional random projections of the random variables. It serves as a surrogate measure of dependence to classic MI that preserves many…
Vision--language models (VLMs) often process visual inputs through a pretrained vision encoder, followed by a projection into the language model's embedding space via a connector component. While crucial for modality fusion, the potential…
Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts…
Region-based image retrieval (RBIR) technique is revisited. In early attempts at RBIR in the late 90s, researchers found many ways to specify region-based queries and spatial relationships; however, the way to characterize the regions, such…
Learning with multiple modalities is crucial for automated brain tumor segmentation from magnetic resonance imaging data. Explicitly optimizing the common information shared among all modalities (e.g., by maximizing the total correlation)…
Feature extraction and description is an important topic of computer vision, as it is the starting point of a number of tasks such as image reconstruction, stitching, registration, and recognition among many others. In this paper, two new…
The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's performance on salient object…
There are many image fusion methods that can be used to produce high-resolution mutlispectral images from a high-resolution panchromatic (PAN) image and low-resolution multispectral (MS) of remote sensed images. This paper attempts to…
In a research context, image acquisition will often involve a pre-defined static protocol and the data will be of high quality. If we are to build applications that work in hospitals without significant operational changes in care delivery,…
Satellites continuously generate massive volumes of data, particularly for Earth observation, including satellite image time series (SITS). However, most deep learning models are designed to process either entire images or complete time…
Since its inception, the neural estimation of mutual information (MI) has demonstrated the empirical success of modeling expected dependency between high-dimensional random variables. However, MI is an aggregate statistic and cannot be used…
This paper presents a method based on a kernel dictionary learning algorithm for segmenting brain tumor regions in magnetic resonance images (MRI). A set of first-order and second-order statistical feature vectors are extracted from patches…
Purpose: To develop a general framework for Parallel Imaging (PI) with the use of Maxwell regularization for the estimation of the sensitivity maps (SMs) and constrained optimization for the parameter-free image reconstruction. Theory and…
Recent progress in computational photography has shown that we can acquire near-infrared (NIR) information in addition to the normal visible (RGB) band, with only slight modifications to standard digital cameras. Due to the proximity of the…
Semantic segmentation requires a detailed labeling of image pixels by object category. Information derived from local image patches is necessary to describe the detailed shape of individual objects. However, this information is ambiguous…
Referring image segmentation aims to segment the target object referred by a natural language expression. However, previous methods rely on the strong assumption that one sentence must describe one target in the image, which is often not…
Image metrics predict the perceived per-pixel difference between a reference image and its degraded (e. g., re-rendered) version. In several important applications, the reference image is not available and image metrics cannot be applied.…