Related papers: Context-Aware Optimal Transport Learning for Retin…
Fundus images are very useful in identifying various ophthalmic disorders. However, due to the presence of artifacts, the visibility of the retina is severely affected. This may result in misdiagnosis of the disorder which may lead to more…
This thesis examines self-attention training through the lens of Optimal Transport (OT) and develops an OT-based alternative for tabular classification. The study tracks intermediate projections of the self-attention layer during training…
Cataracts are the leading cause of vision loss worldwide. Restoration algorithms are developed to improve the readability of cataract fundus images in order to increase the certainty in diagnosis and treatment for cataract patients.…
Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning…
Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method…
Optimal transport is a machine learning problem with applications including distribution comparison, feature selection, and generative adversarial networks. In this paper, we propose feature-robust optimal transport (FROT) for…
We study the use of amortized optimization to predict optimal transport (OT) maps from the input measures, which we call Meta OT. This helps repeatedly solve similar OT problems between different measures by leveraging the knowledge and…
We introduce SceneTransporter, an end-to-end framework for structured 3D scene generation from a single image. While existing methods generate part-level 3D objects, they often fail to organize these parts into distinct instances in…
It is feasible to recognize the presence and seriousness of eye disease by investigating the progressions in retinal biological structure. Fundus examination is a diagnostic procedure to examine the biological structure and anomaly of the…
Recent advances in deep learning, such as powerful generative models and joint text-image embeddings, have provided the computational creativity community with new tools, opening new perspectives for artistic pursuits. Text-to-image…
Diabetic retinopathy (DR) grading from fundus images has attracted increasing interest in both academic and industrial communities. Most convolutional neural network (CNN) based algorithms treat DR grading as a classification task via…
Reliable traversable area segmentation in unstructured environments is critical for planning and decision-making in autonomous driving. However, existing data-driven approaches often suffer from degraded segmentation performance in…
We scrutinise an important observation plaguing scene-level sketch research -- that a significant portion of scene sketches are "partial". A quick pilot study reveals: (i) a scene sketch does not necessarily contain all objects in the…
Cross-domain alignment between two sets of entities (e.g., objects in an image, words in a sentence) is fundamental to both computer vision and natural language processing. Existing methods mainly focus on designing advanced attention…
In contrast to non-medical image denoising, where enhancing image clarity is the primary goal, medical image denoising warrants preservation of crucial features without introduction of new artifacts. However, many denoising methods that…
Optic nerve head (ONH) detection has been a crucial area of study in ophthalmology for years. However, the significant discrepancy between fundus image datasets, each generated using a single type of fundus camera, poses challenges to the…
The automatic diagnosis of various retinal diseases from fundus images is important to support clinical decision-making. However, developing such automatic solutions is challenging due to the requirement of a large amount of human-annotated…
Ultra-Wide-Field (UWF) retinal imaging has revolutionized retinal diagnostics by providing a comprehensive view of the retina. However, it often suffers from quality-degrading factors such as blurring and uneven illumination, which obscure…
Identifying lesions in fundus images is an important milestone toward an automated and interpretable diagnosis of retinal diseases. To support research in this direction, multiple datasets have been released, proposing groundtruth maps for…
Multi-label image classification is a prediction task that aims to identify more than one label from a given image. This paper considers the semantic consistency of the latent space between the visual patch and linguistic label domains and…