Related papers: MESA: A Training-Free Multi-Exemplar Deep Framewor…

Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.…

Face restoration from low resolution and noise is important for applications of face analysis recognition. However, most existing face restoration models omit the multiple scale issues in face restoration problem, which is still not…

Feature detection is an important procedure for image matching, where unsupervised feature detection methods are the detection approaches that have been mostly studied recently, including the ones that are based on repeatability requirement…

We propose a Multiscale Invertible Generative Network (MsIGN) and associated training algorithm that leverages multiscale structure to solve high-dimensional Bayesian inference. To address the curse of dimensionality, MsIGN exploits the…

The advancement of sensing technology has driven the widespread application of high-dimensional data. However, issues such as missing entries during acquisition and transmission negatively impact the accuracy of subsequent tasks. Tensor…

Ultrasound Strain Elastography (USE) is a powerful non-invasive imaging technique for assessing tissue mechanical properties, offering crucial diagnostic value across diverse clinical applications. However, its clinical application remains…

MRI is an inherently slow process, which leads to long scan time for high-resolution imaging. The speed of acquisition can be increased by ignoring parts of the data (undersampling). Consequently, this leads to the degradation of image…

In this paper, we introduce a novel method for merging the weights of multiple pre-trained neural networks using a genetic algorithm called MeGA. Traditional techniques, such as weight averaging and ensemble methods, often fail to fully…

Currently, the destruction of the sequence structure in handwritten text has become one of the main bottlenecks restricting the recognition task. The typical situations include additional specific markers (the text swapping modification)…

Semantic editing on segmentation map has been proposed as an intermediate interface for image generation, because it provides flexible and strong assistance in various image generation tasks. This paper aims to improve quality of edited…

We introduce InverseFaceNet, a deep convolutional inverse rendering framework for faces that jointly estimates facial pose, shape, expression, reflectance and illumination from a single input image. By estimating all parameters from just a…

Cultural heritage preservation increasingly demands non-invasive digital methods for painting restoration, yet identifying and restoring fine craquelure patterns from complex brushstrokes remains challenging due to scarce pixel-level…

Self-supervised learning (SSL) has recently emerged as a key strategy for building foundation models in remote sensing, where the scarcity of annotated data limits the applicability of fully supervised approaches. In this work, we introduce…

Compressed Sensing MRI (CS-MRI) has provided theoretical foundations upon which the time-consuming MRI acquisition process can be accelerated. However, it primarily relies on iterative numerical solvers which still hinders their adaptation…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

Recently, text classification model based on graph neural network (GNN) has attracted more and more attention. Most of these models adopt a similar network paradigm, that is, using pre-training node embedding initialization and two-layer…

Pre-training has been an important ingredient in developing strong monocular depth estimation models in recent years. For instance, self-supervised learning (SSL) is particularly effective by alleviating the need for large datasets with…

This paper explores Masked Autoencoders (MAE) with Gaussian Splatting. While reconstructive self-supervised learning frameworks such as MAE learns good semantic abstractions, it is not trained for explicit spatial awareness. Our approach,…

Modern ultra-high-resolution image synthesis relies heavily on the robust generative capacity of large-scale pre-trained Latent Diffusion Models (LDMs). While recent representation alignment methods have proven effective by distilling…

The Multiple Sequence Alignment (MSA) is a computational abstraction that represents a partial summary either of indel history, or of structural similarity. Taking the former view (indel history), it is possible to use formal automata…