Related papers: Meta-learning based Selective Fixed-filter Active …

Learning with noisy labels has become imperative in the Big Data era, which saves expensive human labors on accurate annotations. Previous noise-transition-based methods have achieved theoretically-grounded performance under the…

Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. However, the majority of existing defense methods are tailored to defend against a…

Recording channel mismatch between training and testing conditions has been shown to be a serious problem for speech separation. This situation greatly reduces the separation performance, and cannot meet the requirement of daily use. In…

In this paper, we present a novel information processing architecture for safe deep learning-based visual navigation of autonomous systems. The proposed information processing architecture is used to support a perceptual attention-based…

This paper proposes CANC, a Co-teaching Active Noise Cancellation method, applied in spatial computing to address deep learning trained with extreme noisy labels. Deep learning algorithms have been successful in spatial computing for land…

Convolution neural networks have achieved remarkable performance in many tasks of computing vision. However, CNN tends to bias to low frequency components. They prioritize capturing low frequency patterns which lead them fail when suffering…

Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation resources (e.g., model size, running memory). To address this…

There is a need for fast adaptation in spike sorting algorithms to implement brain-machine interface (BMIs) in different applications. Learning and adapting the functionality of the sorting process in real-time can significantly improve the…

Automated respiratory sound classification faces practical challenges from background noise and insufficient denoising in existing systems. We propose Adaptive Differential Denoising network, that integrates noise suppression and…

Various neural network architectures have been proposed in recent years for the task of multi-channel speech separation. Among them, the filter-and-sum network (FaSNet) performs end-to-end time-domain filter-and-sum beamforming and has…

Deep Learning is considered to be a quite young in the area of machine learning research, found its effectiveness in dealing complex yet high dimensional dataset that includes but limited to images, text and speech etc. with multiple levels…

Audio and visual signals typically occur simultaneously, and humans possess an innate ability to correlate and synchronize information from these two modalities. Recently, a challenging problem known as Audio-Visual Segmentation (AVS) has…

Deep learning methods have been considered promising for accelerating molecular screening in drug discovery and material design. Due to the limited availability of labelled data, various self-supervised molecular pre-training methods have…

Fluid antenna systems (FAS) offer remarkable spatial flexibility but face significant challenges in acquiring high-resolution channel state information (CSI), leading to considerable overhead. To address this issue, we propose CANet, a…

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks…

Existing fixed pattern noise reduction (FPNR) methods are easily affected by the motion state of the scene and working condition of the image sensor, which leads to over smooth effects, ghosting artifacts as well as slow convergence rate.…

Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep…

Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs - as these systems often process user-generated text or follow an error-prone upstream component. To this end, we formulate the…

Most deep learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these…

When a channel model is available, learning how to communicate on fading noisy channels can be formulated as the (unsupervised) training of an autoencoder consisting of the cascade of encoder, channel, and decoder. An important limitation…