Recent generative adversarial network (GAN) based methods (e. g., CycleGAN) are prone to fail at preserving image-objects in image-to-image translation, which reduces their practicality on tasks such as domain adaptation.
Despite an increased demand for valuable data, the privacy concerns associated with sensitive datasets present a barrier to data sharing.
However, the sensitive information in the datasets discourages data owners from releasing these datasets.
Domain shift between medical images from multicentres is still an open question for the community, which degrades the generalization performance of deep learning models.
Due to the wide existence and large morphological variances of nuclei, accurate nuclei instance segmentation is still one of the most challenging tasks in computational pathology.
A novel pseudo-label (namely self-loop uncertainty), generated by recurrently optimizing the neural network with a self-supervised task, is adopted as the ground-truth for the unlabeled images to augment the training set and boost the segmentation accuracy.
We verify our light-weighted neural network on four sets of bitemporal SAR images.
Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset.
We present a novel variational generative adversarial network (VGAN) based on Wasserstein loss to learn a latent representation from a face image that is invariant to identity but preserves head-pose information.
Convolutional Neural Network (CNN) or Long short-term memory (LSTM) based models with the input of spectrogram or waveforms are commonly used for deep learning based audio source separation.
Ranked #16 on Music Source Separation on MUSDB18
In this letter, we proposed a spatial metric learning method to obtain a difference image more robust to the speckle by learning a metric from a set of constraint pairs.
Change detection is a quite challenging task due to the imbalance between unchanged and changed class.
Two approaches are widely used in the literature to fuse multiple modalities in the segmentation networks: early-fusion (which stacks multiple modalities as different input channels) and late-fusion (which fuses the segmentation results from different modalities at the very end).
Second, given a meta path, nodes in HIN are connected by path instances while existing works fail to fully explore the differences between path instances that reflect nodes' preferences in the semantic space.
In this paper, we consider a typical image blind denoising problem, which is to remove unknown noise from noisy images.