Related papers: Denoising convolutional autoencoder based B-mode u…
Convolutional denoising autoencoders (DAEs) are powerful tools for image restoration. However, they inherit a key limitation of convolutional neural networks (CNNs): they tend to recover low-frequency features, such as smooth regions, more…
In the past few decades, to reduce the risk of X-ray in computed tomography (CT), low-dose CT image denoising has attracted extensive attention from researchers, which has become an important research issue in the field of medical images.…
In zero-resource settings where transcribed speech audio is unavailable, unsupervised feature learning is essential for downstream speech processing tasks. Here we compare two recent methods for frame-level acoustic feature learning. For…
In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off. This paper introduces a novel and scalable approach for…
A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual…
Deep neural networks have been widely used in image denoising during the past few years. Even though they achieve great success on this problem, they are computationally inefficient which makes them inappropriate to be implemented in mobile…
Environmental audio tagging aims to predict only the presence or absence of certain acoustic events in the interested acoustic scene. In this paper we make contributions to audio tagging in two parts, respectively, acoustic modeling and…
Ultrafast electron beam X-ray computed tomography produces noisy data due to short measurement times, causing reconstruction artifacts and limiting overall image quality. To counteract these issues, two self-supervised deep learning methods…
Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high…
This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretical summarize the general properties of all algorithms that are based on traditional Auto-Encoders:…
Discriminative features extracted from the sparse coding model have been shown to perform well for classification. Recent deep learning architectures have further improved reconstruction in inverse problems by considering new dense priors…
With the inexorable digitalisation of the modern world, every subset in the field of technology goes through major advancements constantly. One such subset is digital images which are ever so popular. Images can not always be as visually…
Masked autoencoder (MAE) has attracted unprecedented attention and achieves remarkable performance in many vision tasks. It reconstructs random masked image patches (known as proxy task) during pretraining and learns meaningful semantic…
Epilepsy is one of the most common neurological disorders. This disease requires reliable and efficient seizure detection methods. Electroencephalography (EEG) is the gold standard for seizure monitoring, but its manual analysis is a…
Unsupervised anomalous sound detection (ASD) aims to detect unknown anomalous sounds of devices when only normal sound data is available. The autoencoder (AE) and self-supervised learning based methods are two mainstream methods. However,…
Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…
In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in…
Binary change detection in bi-temporal co-registered hyperspectral images is a challenging task due to a large number of spectral bands present in the data. Researchers, therefore, try to handle it by reducing dimensions. The proposed work…
We present an unsupervised 3D shape co-segmentation method which learns a set of deformable part templates from a shape collection. To accommodate structural variations in the collection, our network composes each shape by a selected subset…
Masked auto-encoder pre-training has emerged as a prevalent technique for initializing and enhancing dense retrieval systems. It generally utilizes additional Transformer decoder blocks to provide sustainable supervision signals and…