Related papers: Code-Aligned Autoencoders for Unsupervised Change …
Unsupervised image-to-image translation is used to transform images from a source domain to generate images in a target domain without using source-target image pairs. Promising results have been obtained for this problem in an adversarial…
Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only…
Supervised deep learning models depend on massive labeled data. Unfortunately, it is time-consuming and labor-intensive to collect and annotate bitemporal samples containing desired changes. Transfer learning from pre-trained models is…
Unsupervised domain adaptation (UDA) methods have shown their promising performance in the cross-modality medical image segmentation tasks. These typical methods usually utilize a translation network to transform images from the source…
Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their…
Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail…
Recent advances of image-to-image translation focus on learning the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation. However, the existing methods only consider one of the two perspectives, which…
Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…
Recent image-to-image translation works have been transferred from supervised to unsupervised settings due to the expensive cost of capturing or labeling large amounts of paired data. However, current unsupervised methods using the…
We propose a novel machine learning strategy for studying neuroanatomical shape variation. Our model works with volumetric binary segmentation images, and requires no pre-processing such as the extraction of surface points or a mesh. The…
Unsupervised domain adaptation is a promising technique for semantic segmentation and other computer vision tasks for which large-scale data annotation is costly and time-consuming. In semantic segmentation, it is attractive to train models…
Subsurface imaging involves solving full waveform inversion (FWI) to predict geophysical properties from measurements. This problem can be reframed as an image-to-image translation, with the usual approach being to train an encoder-decoder…
Recently developed deep learning models are able to learn to segment scenes into component objects without supervision. This opens many new and exciting avenues of research, allowing agents to take objects (or entities) as inputs, rather…
Supervised learning is based on the assumption that the ground truth in the training data is accurate. However, this may not be guaranteed in real-world settings. Inaccurate training data will result in some unexpected predictions. In image…
Lane detection is crucial for vehicle localization which makes it the foundation for automated driving and many intelligent and advanced driving assistant systems. Available vision-based lane detection methods do not make full use of the…
Earth observation with small satellites serves a wide range of relevant applications. However, significant advances in sensor technology (e.g., higher resolution, multiple spectrums beyond visible light) in combination with challenging…
Geometric alignment appears in a variety of applications, ranging from domain adaptation, optimal transport, and normalizing flows in machine learning; optical flow and learned augmentation in computer vision and deformable registration…
In this paper, we build autoencoder based pipelines for extreme end-to-end image compression based on Ball\'e's approach, which is the state-of-the-art open source implementation in image compression using deep learning. We deepened the…
We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits. Among all possible algorithms that use this information, ours finds the…
We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type…