Related papers: BasisNet: Two-stage Model Synthesis for Efficient …

In our previous work, we proposed a neural vocoder called APNet, which directly predicts speech amplitude and phase spectra with a 5 ms frame shift in parallel from the input acoustic features, and then reconstructs the 16 kHz speech…

We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via ad hoc…

The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data processing can be enabled by deploying pretrained models, the…

General aviation fault diagnosis and efficient maintenance are critical to flight safety; however, deploying deep learning models on resource-constrained edge devices poses dual challenges in computational capacity and interpretability.…

Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performances on previously learned ones…

In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the argument that such a partial gradient is close to the true…

While machine learning is widely used to optimize wireless networks, training a separate model for each task in communication and localization is becoming increasingly unsustainable due to the significant costs associated with training and…

XNet introduces a wavelet-based X-shaped unified architecture for fully- and semi-supervised biomedical segmentation. So far, however, XNet still faces the limitations, including performance degradation when images lack high-frequency (HF)…

In this work, we explore whether modeling recurrence into the Transformer architecture can both be beneficial and efficient, by building an extremely simple recurrent module into the Transformer. We compare our model to baselines following…

Automatic meeting summarization is becoming increasingly popular these days. The ability to automatically summarize meetings and to extract key information could greatly increase the efficiency of our work and life. In this paper, we…

Modelling river physical processes is of critical importance for flood protection, river management and restoration of riverine environments. Developments in algorithms and computational power have led to a wider spread of river simulation…

The practical application requests both accuracy and efficiency on multi-person pose estimation algorithms. But the high accuracy and fast inference speed are dominated by top-down methods and bottom-up methods respectively. To make a…

Deep neural networks (DNN) have achieved remarkable success in computer vision (CV). However, training and inference of DNN models are both memory and computation intensive, incurring significant overhead in terms of energy consumption and…

Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to…

Deep neural networks have been proven effective in a wide range of tasks. However, their high computational and memory costs make them impractical to deploy on resource-constrained devices. To address this issue, quantization schemes have…

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…

Visual saliency detection tries to mimic human vision psychology which concentrates on sparse, important areas in natural image. Saliency prediction research has been traditionally based on low level features such as contrast, edge, etc.…

Continual learning (CL) aims to learn new tasks while retaining past knowledge, addressing the challenge of forgetting during task adaptation. Rehearsal-based methods, which replay previous samples, effectively mitigate forgetting. However,…

Large number of weights in deep neural networks makes the models difficult to be deployed in low memory environments such as, mobile phones, IOT edge devices as well as "inferencing as a service" environments on cloud. Prior work has…

In view of the recent paradigm shift in deep AI based image processing methods, medical image processing has advanced considerably. In this study, we propose a novel deep neural network (DNN), entitled InceptNet, in the scope of medical…