Over the past decade, the dominance of deep learning has prevailed across various
domains of artificial intelligence, including natural language processing, computer vision …

In recent years, it has been witnessed that the systolic array is a successful architecture for
DNN hardware accelerators. However, the design of systolic arrays also encountered many …

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

Inspired by the long-range modeling ability of ViTs large-kernel convolutions are widely
studied and adopted recently to enlarge the receptive field and improve model performance …

This paper presents a new vision Transformer, Scale Aware Modulation Transformer (SMT),
that can handle various downstream tasks efficiently by combining the convolutional network …

Efficient neural network backbones for mobile devices are often optimized for metrics such
as FLOPs or parameter count. However, these metrics may not correlate well with latency of …

Abstract We present Mobile-Former, a parallel design of MobileNet and transformer with a
two-way bridge in between. This structure leverages the advantages of MobileNet at local …

Vision Transformers have been the most popular network architecture in visual recognition
recently due to the strong ability of encode global information. However, its high …

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

This paper introduces EfficientNetV2, a new family of convolutional networks that have faster
training speed and better parameter efficiency than previous models. To develop these …