Vision transformers have shown great success due to their high model capabilities.
However, their remarkable performance is accompanied by heavy computation costs, which …

The network attack detection model based on machine learning (ML) has received extensive
attention and research in PMU measurement data protection of power systems. However …

Compressive autoencoders (CAEs) play an important role in deep learning-based image
compression, but large-scale CAEs are computationally expensive. We propose a …

Few-shot semantic segmentation (FSS) has been developed to perform pixel-level
segmentation with only a few dense labeled examples for training, which relieves the …

Abstract To deploy Convolutional Neural Networks (CNNs) on resource-limited devices,
binary CNNs with 1-bit activations and weights prove to be a promising approach …

Video Anomaly detection, aiming to detect the abnormal behaviors in surveillance videos, is
a challenging task since the anomalous events are diversified and complicated in different …

Most image retrieval works aim at learning discriminative visual features, while little attention
is paid to the retrieval efficiency. The speed of feature extraction is key to the real-world …

In this paper, we introduce AttendEM, a framework for entity matching (EM), ie, pairwise
identification of duplicates across databases. Eschewing the prevalent focus on text …

One-shot Neural architecture search (One-shot NAS) has been proposed as a time-efficient
approach to obtain optimal subnet architectures and weights under different complexity …

Recent advancements in deep convolutional neural networks have significantly improved
the performance of saliency prediction. However, the manual configuration of the neural …