Related papers: Siamese Basis Function Networks for Data-efficient…

Material segmentation is a complex task, particularly when dealing with aerial data in poor lighting and atmospheric conditions. To address this, hyperspectral data from specialized cameras can be very useful in addition to RGB images.…

Seismic processing transforms raw data into subsurface images essential for geophysical applications. Traditional methods face challenges, such as noisy data, and manual parameter tuning, among others. Recently deep learning approaches have…

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot segmentation methods first pre-train models on 'seen' classes, and then evaluate their generalization…

In recent years, self-supervised learning has had significant success in applications involving computer vision and natural language processing. The type of pretext task is important to this boost in performance. One common pretext task is…

Semantic segmentation for medical 3D image stacks enables accurate volumetric reconstructions, computer-aided diagnostics and follow up treatment planning. In this work, we present a novel variant of the Unet model called the NUMSnet that…

Hyperspectral images (HSI) have become popular for analysing remotely sensed images in multiple domain like agriculture, medical. However, existing models struggle with complex relationships and characteristics of spectral-spatial data due…

Visual Servoing (VS), where images taken from a camera typically attached to the robot end-effector are used to guide the robot motions, is an important technique to tackle robotic tasks that require a high level of accuracy. We propose a…

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…

Recent deepfake detection studies often treat unseen sample detection as a ``zero-shot" task, training on images generated by known models but generalizing to unknown ones. A key real-world challenge arises when a model performs poorly on…

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…

Data-efficient image classification using deep neural networks in settings, where only small amounts of labeled data are available, has been an active research area in the recent past. However, an objective comparison between published…

Deep learning (DL) has been widely applied into hyperspectral image (HSI) classification owing to its promising feature learning and representation capabilities. However, limited by the spatial resolution of sensors, existing DL-based…

Existing deep Thermal InfraRed (TIR) trackers only use semantic features to describe the TIR object, which lack the sufficient discriminative capacity for handling distractors. This becomes worse when the feature extraction network is only…

Transforming in-situ transmission electron microscopy (TEM) imaging into a tool for spatially-resolved operando characterization of solid-state reactions requires automated, high-precision semantic segmentation of dynamically evolving…

Robotic surgery has become a powerful tool for performing minimally invasive procedures, providing advantages in dexterity, precision, and 3D vision, over traditional surgery. One popular robotic system is the da Vinci surgical platform,…

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

Image classification is one of the main drivers of the rapid developments in deep learning with convolutional neural networks for computer vision. So is the analogous task of scene classification in remote sensing. However, in contrast to…

Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…

Advances in high resolution remote sensing image analysis are currently hampered by the difficulty of gathering enough annotated data for training deep learning methods, giving rise to a variety of small datasets and associated…

Deep neural networks have become a foundational tool for addressing imaging inverse problems. They are typically trained for a specific task, with a supervised loss to learn a mapping from the observations to the image to recover. However,…