Related papers: Guided Context Gating: Learning to leverage salien…

Diabetic retinopathy is the most important complication of diabetes. Early diagnosis of retinal lesions helps to avoid visual loss or blindness. Due to high-resolution and small-size lesion regions, applying existing methods, such as…

Retinal fundus photography offers a non-invasive way to diagnose and monitor a variety of retinal diseases, but is prone to inherent quality glitches arising from systemic imperfections or operator/patient-related factors. However,…

Convolutional Neural Networks (CNNs) have successfully been used to classify diabetic retinopathy (DR) fundus images in recent times. However, deeper representations in CNNs may capture higher-level semantics at the expense of spatial…

Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them.…

We propose a novel attention gate (AG) model for medical image analysis that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs implicitly learn to suppress irrelevant regions in an input…

Accurate retinal vessel segmentation is a challenging problem in color fundus image analysis. An automatic retinal vessel segmentation system can effectively facilitate clinical diagnosis and ophthalmological research. Technically, this…

Objective: This work addresses two key problems of skin lesion classification. The first problem is the effective use of high-resolution images with pretrained standard architectures for image classification. The second problem is the high…

Accurately segmenting blood vessels in retinal fundus images is crucial in the early screening, diagnosing, and evaluating some ocular diseases, yet it poses a nontrivial uncertainty for the segmentation task due to various factors such as…

Retinal image analysis is crucial for diagnosing and treating eye diseases, yet generating accurate medical reports from images remains challenging due to variability in image quality and pathology, especially with limited labeled data.…

Attention has long been proposed by psychologists as important for effectively dealing with the enormous sensory stimulus available in the neocortex. Inspired by the visual attention models in computational neuroscience and the need of…

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…

Diabetic Retinopathy (DR) is a primary cause of blindness, necessitating early detection and diagnosis. This paper focuses on referable DR classification to enhance the applicability of the proposed method in clinical practice. We develop…

When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast, current multimodal large language models (MLLMs) attend to…

Global contexts in images are quite valuable in image-to-image translation problems. Conventional attention-based and graph-based models capture the global context to a large extent, however, these are computationally expensive. Moreover,…

Recently, there has been a growing interest in developing saliency methods that provide visual explanations of network predictions. Still, the usability of existing methods is limited to image classification models. To overcome this…

Retinal lesions play a vital role in the accurate classification of retinal abnormalities. Many researchers have proposed deep lesion-aware screening systems that analyze and grade the progression of retinopathy. However, to the best of our…

The use of attention models for automated image captioning has enabled many systems to produce accurate and meaningful descriptions for images. Over the years, many novel approaches have been proposed to enhance the attention process using…

Manually annotating medical images is extremely expensive, especially for large-scale datasets. Self-supervised contrastive learning has been explored to learn feature representations from unlabeled images. However, unlike natural images,…

Forensic analysis of manipulated pixels requires the identification of various hidden and subtle features from images. Conventional image recognition models generally fail at this task because they are biased and more attentive toward the…

Neural machine translation (NMT) heavily relies on an attention network to produce a context vector for each target word prediction. In practice, we find that context vectors for different target words are quite similar to one another and…