相关论文: Vision-Language Model for Accurate Crater Detectio…

Strong Lensing is a powerful probe of the matter distribution in galaxies and clusters and a relevant tool for cosmography. Analyses of strong gravitational lenses with Deep Learning have become a popular approach due to these astronomical…

Vision-language models like CLIP demonstrate impressive zero-shot generalization but remain highly vulnerable to adversarial attacks. In this work, we propose Confidence-Aware Weighting (CAW) to enhance zero-shot robustness in…

Early identification of patients at risk of cardiovascular diseases (CVD) is crucial for effective preventive care, reducing healthcare burden, and improving patients' quality of life. This study demonstrates the potential of retinal…

Deep Learning (DL) has emerged as a powerful tool for vulnerability detection, often outperforming traditional solutions. However, developing effective DL models requires large amounts of real-world data, which can be difficult to obtain in…

Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning. Compared to standard object detection, the OWOD setting is task to: 1) detect objects seen during…

Vision-language models such as CLIP have boosted the performance of open-vocabulary object detection, where the detector is trained on base categories but required to detect novel categories. Existing methods leverage CLIP's strong…

Exploring open-world situations in an end-to-end manner is a promising yet challenging task due to the need for strong generalization capabilities. In particular, end-to-end autonomous driving in unstructured outdoor environments often…

Blind deconvolution aims to recover an original image from a blurred version in the case where the blurring kernel is unknown. It has wide applications in diverse fields such as astronomy, microscopy, and medical imaging. Blind…

Accurate lane detection is essential for effective path planning and lane following in autonomous driving, especially in scenarios with significant occlusion from vehicles and pedestrians. Existing models often struggle under such…

Designing robust machine learning systems remains an open problem, and there is a need for benchmark problems that cover both environmental changes and evaluation on a downstream task. In this work, we introduce AVOIDDS, a realistic object…

Multiple-surface segmentation in Optical Coherence Tomography (OCT) images is a challenge problem, further complicated by the frequent presence of weak image boundaries. Recently, many deep learning (DL) based methods have been developed…

Fall detection, particularly critical for high-risk demographics like the elderly, is a key public health concern where timely detection can greatly minimize harm. With the advancements in radio frequency technology, radar has emerged as a…

Optical Coherence Tomography Angiography (OCTA) is a non-invasive and non-contacting imaging technique providing visualization of microvasculature of retina and optic nerve head in human eyes in vivo. The adequate image quality of OCTA is…

Optimizing vision models purely for classification accuracy can impose an alignment tax, degrading human-like scanpaths and limiting interpretability. We introduce EVA, a neuroscience-inspired hard-attention mechanistic testbed that makes…

Skin cancer detection still represents a major challenge in healthcare. Common detection methods can be lengthy and require human assistance which falls short in many countries. Previous research demonstrates how convolutional neural…

Early and accurate classification of retinal diseases is critical to counter vision loss and for guiding clinical management of retinal diseases. In this study, we proposed a deep learning method for retinal disease classification utilizing…

Early identification of drought stress in crops is vital for implementing effective mitigation measures and reducing yield loss. Non-invasive imaging techniques hold immense potential by capturing subtle physiological changes in plants…

Depth estimation (DE) provides spatial information about a scene and enables tasks such as 3D reconstruction, object detection, and scene understanding. Recently, there has been an increasing interest in using deep learning (DL)-based…

Deep Learning has shown outstanding results in computer vision tasks; healthcare is no exception. However, there is no straightforward way to expose the decision-making process of DL models. Good accuracy is not enough for skin cancer…

Change detection in satellite imagery seeks to find occurrences of targeted changes in a given scene taken at different instants. This task has several applications ranging from land-cover mapping, to anthropogenic activity monitory as well…