Related papers: Cross-Scale Pretraining: Enhancing Self-Supervised…
Recently, lots of deep networks are proposed to improve the quality of predicted super-resolution (SR) images, due to its widespread use in several image-based fields. However, with these networks being constructed deeper and deeper, they…
Obtaining high-resolution (HR) segmentations from coarse annotations is a pervasive challenge in computer vision. Applications include inferring pixel-level segmentations from token-level labels in vision transformers, upsampling coarse…
Supervised fine-tuning methods (SFT) perform great efficiency on artificial intelligence interpretation in SAR images, leveraging the powerful representation knowledge from pre-training models. Due to the lack of domain-specific pre-trained…
State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former - best represented by sparse coding techniques - strive to exploit intrinsic prior knowledge about the unknown…
Quantifying the perceptual similarity of two images is a long-standing problem in low-level computer vision. The natural image domain commonly relies on supervised learning, e.g., a pre-trained VGG, to obtain a latent representation.…
Most self-supervised video representation learning approaches focus on action recognition. In contrast, in this paper we focus on self-supervised video learning for movie understanding and propose a novel hierarchical self-supervised…
Deep learning (DL) finds rich applications in the wireless domain to improve spectrum awareness. Typically, DL models are either randomly initialized following a statistical distribution or pretrained on tasks from other domains in the form…
In this work, we assess several deep learning strategies for hyperspectral pansharpening. First, we present a new dataset with a greater extent than any other in the state of the art. This dataset, collected using the ASI PRISMA satellite,…
Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to…
Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…
With the current ubiquity of deep learning methods to solve computer vision and remote sensing specific tasks, the need for labelled data is growing constantly. However, in many cases, the annotation process can be long and tedious…
Hyperspectral super-resolution (HSR) is a problem that aims to estimate an image of high spectral and spatial resolutions from a pair of co-registered multispectral (MS) and hyperspectral (HS) images, which have coarser spectral and spatial…
Super-resolution ultrasound imaging (SRUS) is an active area of research as it brings up to a ten-fold improvement in the resolution of microvascular structures. The limitations to the clinical adoption of SRUS include long acquisition…
Remote sensing understanding inherently requires multi-resolution observation, since different targets and application tasks demand different levels of spatial detail. While low-resolution (LR) imagery enables efficient global observation,…
This paper briefly introduces the solutions developed by our team, HFUT-VUT, for Track 1 of self-supervised heart rate measurement in the 3rd Vision-based Remote Physiological Signal Sensing (RePSS) Challenge hosted at IJCAI 2024. The goal…
Collecting large annotated datasets in Remote Sensing is often expensive and thus can become a major obstacle for training advanced machine learning models. Common techniques of addressing this issue, based on the underlying idea of…
Hyperspectral images are crucial for many research works. Spectral super-resolution (SSR) is a method used to obtain high spatial resolution (HR) hyperspectral images from HR multispectral images. Traditional SSR methods include…
Automatic supervised classification with complex modelling such as deep neural networks requires the availability of representative training data sets. While there exists a plethora of data sets that can be used for this purpose, they are…
Since large number of high-quality remote sensing images are readily accessible, exploiting the corpus of images with less manual annotation draws increasing attention. Self-supervised models acquire general feature representations by…
Deep metrics have been shown effective as similarity measures in multi-modal image registration; however, the metrics are currently constructed from aligned image pairs in the training data. In this paper, we propose a strategy for learning…