Self-attention based models such as vision transformers (ViTs) have emerged as a very
competitive architecture alternative to convolutional neural networks (CNNs) in computer …

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 …

Neural architecture search (NAS) has shown promising results discovering models that are
both accurate and fast. For NAS, training a one-shot model has become a popular strategy …

Channel pruning has become an effective yet still challenging approach to achieve compact
neural networks. It aims to prune the optimal set of filters whose removal results in minimal …

This work presents DANCE, a differentiable approach towards the co-exploration of
hardware accelerator and network architecture design. At the heart of DANCE is a …

Real-time semantic segmentation of remote sensing imagery is a challenging task that
requires a tradeoff between effectiveness and efficiency. It has many applications, including …

For deployment, neural architecture search should be hardware-aware, in order to satisfy
the device-specific constraints (eg, memory usage, latency and energy consumption) and …

In one-shot NAS, sub-networks need to be searched from the supernet to meet different
hardware constraints. However, the search cost is high and N times of searches are needed …

A deep-rooted strategy for building convolutional neural networks in computer vision is to
increase the number of filters every time the feature map resolution is decreased. The notion …

For deployment, neural architecture search should be hardware-aware, in order to satisfy
the device-specific constraints (eg, memory usage, latency and energy consumption) and …