Related papers: Adapting Vision Foundation Models for Robust Cloud…
Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly large volume of medical images that need to be processed. It…
Quantitative measurement of crystals in high-resolution images allows for important insights into underlying material characteristics. Deep learning has shown great progress in vision-based automatic crystal size measurement, but current…
Large-scale point cloud semantic segmentation is an important task in 3D computer vision, which is widely applied in autonomous driving, robotics, and virtual reality. Current large-scale point cloud semantic segmentation methods usually…
Foundation models, often pre-trained with large-scale data, have achieved paramount success in jump-starting various vision and language applications. Recent advances further enable adapting foundation models in downstream tasks efficiently…
Transformers have demonstrated remarkable performance in natural language processing and computer vision. However, existing vision Transformers struggle to learn from limited medical data and are unable to generalize on diverse medical…
Foundation models have garnered increasing attention for representation learning in remote sensing. Many such foundation models adopt approaches that have demonstrated success in computer vision with minimal domain-specific modification.…
The demand for high-resolution subsurface imaging and continuous Earth monitoring has driven rapid growth in active and passive seismic data from dense geophone deployments, distributed acoustic sensing (DAS) arrays, and large-scale 2D and…
Object recognition from live video streams comes with numerous challenges such as the variation in illumination conditions and poses. Convolutional neural networks (CNNs) have been widely used to perform intelligent visual object…
Optical remote sensing imagery is indispensable for Earth observation, yet persistent cloud occlusion limits its downstream utility. Most cloud removal (CR) methods are optimized for low-level fidelity and can over-smooth textures and…
Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various applications. However, in case we have multiple views of…
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…
Remote sensing imagery has attracted significant attention in recent years due to its instrumental role in global environmental monitoring, land usage monitoring, and more. As image databases grow each year, performing automatic…
Medical image segmentation plays an important role in many image-guided clinical approaches. However, existing segmentation algorithms mostly rely on the availability of fully annotated images with pixel-wise annotations for training, which…
Medical image segmentation in X-ray images is beneficial for computer-aided diagnosis and lesion localization. Existing methods mainly fall into a centralized learning paradigm, which is inapplicable in the practical medical scenario that…
The transformation of features from 2D perspective space to 3D space is essential to multi-view 3D object detection. Recent approaches mainly focus on the design of view transformation, either pixel-wisely lifting perspective view features…
Executing multiple tasks simultaneously in medical image analysis, including segmentation, classification, detection, and regression, often introduces significant challenges regarding model generalizability and the optimization of shared…
As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapted to real images without requiring their annotations. This…
Semantic segmentation is essential for analyzing highdefinition remote sensing images (HRSIs) because it allows the precise classification of objects and regions at the pixel level. However, remote sensing data present challenges owing to…
Neural networks achieve state-of-the-art performance in many supervised learning tasks when the training data distribution matches the test data distribution. However, their performance drops significantly under domain (covariate) shift, a…
Semantic segmentation serves as a cornerstone of scene understanding in autonomous driving but continues to face significant challenges under complex conditions such as occlusion. Light field and LiDAR modalities provide complementary…