Abstract: Oriented object detection has been developed rapidly in the past few years, where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction ...
Abstract: Convolutional neural networks (CNNs) are computationally demanding due to expensive Multiply-ACcumulate (MAC) operations. Emerging neural network models, such as AdderNet, exploit efficient ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results