Related papers: Reg-TTR, Test-Time Refinement for Fast, Robust and…

Robustness certification, which aims to formally certify the predictions of neural networks against adversarial inputs, has become an integral part of important tool for safety-critical applications. Despite considerable progress, existing…

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in…

Image registration, the process of aligning two or more images, is the core technique of many (semi-)automatic medical image analysis tasks. Recent studies have shown that deep learning methods, notably convolutional neural networks…

We introduce RetinaRegNet, a zero-shot image registration model designed to register retinal images with minimal overlap, large deformations, and varying image quality. RetinaRegNet addresses these challenges and achieves robust and…

Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important. We propose to simultaneously tackle Performance,…

Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integration of external knowledge. However, when adapting RAG systems to specialized…

Rectified Flow (RF) models have advanced high-quality image and video synthesis via optimal transport theory. However, when applied to image-to-image translation, they still depend on costly multi-step denoising, hindering real-time…

Purpose: Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally network performance should be optimized by drawing the training and testing data from the same domain. In practice, however,…

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that…

Diffusion-based unsupervised image registration has been explored for cardiac cine MR, but expensive multi-step inference limits practical use. We propose FlowReg, a flow-matching framework in displacement field space that achieves strong…

Recent advancements in text-to-image generation have inspired researchers to generate datasets tailored for perception models using generative models, which prove particularly valuable in scenarios where real-world data is limited. In this…

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important for deep models when the test environment…

Non-rigid registration is a necessary but challenging task in medical imaging studies. Recently, unsupervised registration models have shown good performance, but they often require a large-scale training dataset and long training times.…

Experimental protocols at synchrotron light sources typically process and validate data only after an experiment has completed, which can lead to undetected errors and cannot enable online steering. Real-time data analysis can enable both…

Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registration across subjects,…

A fast and accurate algorithm is presented for registering scans from an RGB-D camera on a pan-tilt platform. The pan-tilt RGB-D camera rotates and scans the entire scene in an automated fashion. The proposed algorithm exploits the movement…

Large deep learning models have achieved significant success in various tasks. However, the performance of a model can significantly degrade if it is needed to train on datasets with noisy labels with misleading or ambiguous information. To…

Deep Learning-based end-to-end Automatic Speech Recognition (ASR) has made significant strides but still struggles with performance on out-of-domain samples due to domain shifts in real-world scenarios. Test-Time Adaptation (TTA) methods…

Although Neural Radiance Fields (NeRF) is popular in the computer vision community recently, registering multiple NeRFs has yet to gain much attention. Unlike the existing work, NeRF2NeRF, which is based on traditional optimization methods…

Parameter-efficient tuning (PET) aims to transfer pre-trained foundation models to downstream tasks by learning a small number of parameters. Compared to traditional fine-tuning, which updates the entire model, PET significantly reduces…