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

Real-time object detection is one of the most important research topics in computer vision.
As new approaches regarding architecture optimization and training optimization are …

The recent amalgamation of transformer and convolutional designs has led to steady
improvements in accuracy and efficiency of the models. In this work, we introduce FastViT, a …

Recent vision transformers, large-kernel CNNs and MLPs have attained remarkable
successes in broad vision tasks thanks to their effective information fusion in the global …

Since the introduction of Vision Transformers, the landscape of many computer vision tasks
(eg, semantic segmentation), which has been overwhelmingly dominated by CNNs, recently …

The tradeoff between performance and inference speed is critical for practical applications.
Architecture reparameterization obtains better tradeoffs and it is becoming an increasingly …

Underwater target detection is a crucial aspect of ocean exploration. However, conventional
underwater target detection methods face several challenges such as inaccurate feature …

Road hazards (RH) have always been the cause of many serious traffic accidents. These
have posed a threat to the safety of drivers, passengers, and pedestrians, and have also …

Feature reuse has been a key technique in light-weight convolutional neural networks
(CNNs) design. Current methods usually utilize a concatenation operator to keep large …

We present a hardware-efficient architecture of convolutional neural network, which has a
repvgg-like architecture. Flops or parameters are traditional metrics to evaluate the efficiency …