Related papers: Spatially regularized active diffusion learning fo…

Deep learning-based segmentation techniques have shown remarkable performance in brain segmentation, yet their success hinges on the availability of extensive labeled training data. Acquiring such vast datasets, however, poses a significant…

Diffusion models have recently received increasing research attention for their remarkable transfer abilities in semantic segmentation tasks. However, generating fine-grained segmentation masks with diffusion models often requires…

Image segmentation is a key topic in image processing and computer vision with applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among many…

Hyperspectral image (HSI) analysis plays a critical role in remote sensing, agriculture, and environmental monitoring. However, traditional methods often struggle to handle the high dimensionality, spectral redundancy, and noise inherent in…

In supervised deep learning, learning good representations for remote--sensing images (RSI) relies on manual annotations. However, in the area of remote sensing, it is hard to obtain huge amounts of labeled data. Recently, self--supervised…

It is argued that deep learning is efficient for data that is generated from hierarchal generative models. Examples of such generative models include wavelet scattering networks, functions of compositional structure, and deep rendering…

Diffusion models are gaining widespread use in cutting-edge image, video, and audio generation. Score-based diffusion models stand out among these methods, necessitating the estimation of score function of the input data distribution. In…

Collecting an over-the-air wireless communications training dataset for deep learning-based communication tasks is relatively simple. However, labeling the dataset requires expert involvement and domain knowledge, may involve private…

Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demonstrated that iteratively refining pure Gaussian noise using…

Nuclei segmentation and classification is a significant process in pathology image analysis. Deep learning-based approaches have greatly contributed to the higher accuracy of this task. However, those approaches suffer from the imbalanced…

The need to count and localize repeating objects in an image arises in different scenarios, such as biological microscopy studies, production lines inspection, and surveillance recordings analysis. The use of supervised Convoutional Neural…

Recent advances in deep learning have shown that learning robust feature representations is critical for the success of many computer vision tasks, including medical image segmentation. In particular, both transformer and…

In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consists of multiple relevant labels and other noisy labels. Existing PML methods typically design…

Diffusion models have achieved significant progress in image generation. The pre-trained Stable Diffusion (SD) models are helpful for image deblurring by providing clear image priors. However, directly using a blurry image or pre-deblurred…

Score diffusion methods can learn probability densities from samples. The score of the noise-corrupted density is estimated using a deep neural network, which is then used to iteratively transport a Gaussian white noise density to a target…

Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains due to their creative and high-fidelity image generation. Nonetheless, existing large-scale diffusion models…

Image segmentation is a clustering task whereby each pixel is assigned a cluster label. Remote sensing data usually consists of multiple bands of spectral images in which there exist semantically meaningful land cover subregions,…

Although Convolutional Neural Networks (CNNs) have achieved promising results in image classification, they still are vulnerable to affine transformations including rotation, translation, flip and shuffle. The drawback motivates us to…

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…

Active learning enables the efficient construction of a labeled dataset by labeling informative samples from an unlabeled dataset. In a real-world active learning scenario, considering the diversity of the selected samples is crucial…