Related papers: CARL: Camera-Agnostic Representation Learning for …
Contrastive learning (CL) aims to learn useful representation without relying on expert annotations in the context of medical image segmentation. Existing approaches mainly contrast a single positive vector (i.e., an augmentation of the…
Active learning is considered a viable solution to alleviate the contradiction between the high dependency of deep learning-based segmentation methods on annotated data and the expensive pixel-level annotation cost of medical images.…
Aggregated search aims to construct search result pages (SERPs) from blue-links and heterogeneous modules (such as news, images, and videos). Existing studies have largely ignored the correlations between blue-links and heterogeneous…
Despite their effectiveness, current deep learning models face challenges with images coming from different domains with varying appearance and content. We introduce SegCLR, a versatile framework designed to segment images across different…
This paper introduces a practical and accurate calibration method for camera spectral sensitivity using a diffraction grating. Accurate calibration of camera spectral sensitivity is crucial for various computer vision tasks, including color…
Magnetic Resonance Imaging (MRI) is a widely utilized diagnostic tool in clinical settings, but its application is limited by the relatively long acquisition time. As a result, fast MRI reconstruction has become a significant area of…
Continual learning (CL) over non-stationary data streams remains one of the long-standing challenges in deep neural networks (DNNs) as they are prone to catastrophic forgetting. CL models can benefit from self-supervised pre-training as it…
Large-scale volumetric medical images with annotation are rare, costly, and time prohibitive to acquire. Self-supervised learning (SSL) offers a promising pre-training and feature extraction solution for many downstream tasks, as it only…
The speckle noise inherent in Synthetic Aperture Radar (SAR) imagery significantly degrades image quality and complicates subsequent analysis. Given that SAR speckle is multiplicative and Gamma-distributed, effectively despeckling SAR…
As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection increasingly challenging. Many existing methods exploit frequency-domain cues for…
With the advent of advances in self-supervised learning, paired clean-noisy data are no longer required in deep learning-based image denoising. However, existing blind denoising methods still require the assumption with regard to noise…
Remote sensing data has been widely used for various Earth Observation (EO) missions such as land use and cover classification, weather forecasting, agricultural management, and environmental monitoring. Most existing remote sensing…
Replicating In-Context Learning (ICL) in computer vision remains challenging due to task heterogeneity. We propose \textbf{VIRAL}, a framework that elicits visual reasoning from a pre-trained image editing model by formulating ICL as…
Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels…
There are a multitude of emerging imaging technologies that could benefit robotics. However the need for bespoke models, calibration and low-level processing represents a key barrier to their adoption. In this work we present NOCaL, Neural…
The Segment Anything Model (SAM) has achieved remarkable successes in the realm of natural image segmentation, but its deployment in the medical imaging sphere has encountered challenges. Specifically, the model struggles with medical…
Spatial transcriptomics (ST) is a novel technique that simultaneously captures pathological images and gene expression profiling with spatial coordinates. Since ST is closely related to pathological features such as disease subtypes, it may…
Modern cameras typically offer two types of image states: a minimally processed linear raw RGB image representing the raw sensor data, and a highly-processed non-linear image state, such as the sRGB state. The CIE-XYZ color space is a…
We present a cost-effective new approach for generating denser depth maps for Autonomous Driving (AD) and Autonomous Vehicles (AVs) by integrating the images obtained from deep neural network (DNN) 4D radar detectors with conventional…
We introduce a deep learning (DL) framework for inverse problems in imaging, and demonstrate the advantages and applicability of this approach in passive synthetic aperture radar (SAR) image reconstruction. We interpret image recon-…