Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of
neural networks. There has been a flurry of algorithms that try to solve this practical problem …

In diffusion models, UNet is the most popular network backbone, since its long skip connects
(LSCs) to connect distant network blocks can aggregate long-distant information and …

Most existing neural network pruning methods hand-crafted their importance criteria and
structures to prune. This constructs heavy and unintended dependencies on heuristics and …

The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence
and has successfully boosted the performance of different models. However, current …

Abstract Currently, Sharpness-Aware Minimization (SAM) is proposed to seek the
parameters that lie in a flat region to improve the generalization when training neural …

Filter pruning is advocated for accelerating deep neural networks without dedicated
hardware or libraries, while maintaining high prediction accuracy. Several works have cast …

Federated learning (FL) allows multiple clients to collaboratively learn a globally shared
model through cycles of model aggregation and local model training, without the need to …

Infrared Small Target Detection (IRSTD) refers to detecting faint targets in infrared images,
which has achieved notable progress with the advent of deep learning. However, the drive …

The large-scale simulation of dynamical systems is critical in numerous scientific and
engineering disciplines. However, traditional numerical solvers are limited by the choice of …

Convolutional neural networks (CNNs) have been adopted to classify the remote sensing
scene image. However, the application of these complicated networks on the satellite …