Related papers: Generating Aligned Pseudo-Supervision from Non-Ali…

One of the key limitations in conventional deep learning based image reconstruction is the need for registered pairs of training images containing a set of high-quality groundtruth images. This paper addresses this limitation by proposing a…

Convolutional neural networks (CNNs) have achieved exciting performance in joint segmentation of optic disc and optic cup on single-institution datasets. However, their clinical translation is hindered by two major challenges: limited…

In the absence of labeled target data, unsupervised domain adaptation approaches seek to align the marginal distributions of the source and target domains in order to train a classifier for the target. Unsupervised domain alignment…

Enhancing low-light images while maintaining natural colors is a challenging problem due to camera processing variations and limited access to photos with ground-truth lighting conditions. The latter is a crucial factor for supervised…

Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images of the same category across diverse domains without relying on annotations. Existing UCIR methods, which align cross-domain features for the entire image, often…

This paper addresses unsupervised domain adaptation, the setting where labeled training data is available on a source domain, but the goal is to have good performance on a target domain with only unlabeled data. Like much of previous work,…

The performance of deep learning based image super-resolution (SR) methods depend on how accurately the paired low and high resolution images for training characterize the sampling process of real cameras. Low and high resolution…

Image deraining plays a pivotal role in low-level computer vision, serving as a prerequisite for robust outdoor surveillance and autonomous driving systems. While deep learning paradigms have achieved remarkable success in firmly aligned…

In most studies on learning-based image super-resolution (SR), the paired training dataset is created by downscaling high-resolution (HR) images with a predetermined operation (e.g., bicubic). However, these methods fail to super-resolve…

Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world `wild tasks' where large difference between labeled…

Medical image synthesis generates additional imaging modalities that are costly, invasive or harmful to acquire, which helps to facilitate the clinical workflow. When training pairs are substantially misaligned (e.g., lung MRI-CT pairs with…

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…

In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a new centreor a new…

We present a novel approach for unsupervised domain adaptation (UDA) for natural images. A commonly-used objective for UDA schemes is to enhance domain alignment in representation space even if there is a domain shift in the input space.…

Unsupervised domain adaptive object detection is a challenging vision task where object detectors are adapted from a label-rich source domain to an unlabeled target domain. Recent advances prove the efficacy of the adversarial based domain…

Synthetic data (SIM) drawn from simulators have emerged as a popular alternative for training models where acquiring annotated real-world images is difficult. However, transferring models trained on synthetic images to real-world…

Event-based cameras offer reliable measurements for preforming computer vision tasks in high-dynamic range environments and during fast motion maneuvers. However, adopting deep learning in event-based vision faces the challenge of annotated…

Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods learned on synthetic data do not perform well in…

Class distribution mismatch (CDM) refers to the discrepancy between class distributions in training data and target tasks. Previous methods address this by designing classifiers to categorize classes known during training, while grouping…

Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be…