Event-based cameras are bio-inspired vision sensors that mimic the sparse and asynchronous activation of the animal retina, offering advantages such as low latency and low computational load in ...

Abstract: The convolution modulation jamming method based on noise template has received widespread attention and application due to its advantages such as having the ability to obtain synthetic ...

Abstract: Convolutional neural network (CNN) quantization is an efficient model compression technique primarily used for accelerating inference and optimizing resources. However, existing methods ...

Fusing features from different sources is a critical aspect of many computer vision tasks. Existing approaches can be roughly categorized as parameter-free or learnable operations. However, ...

A new brain-inspired AI method called Lp-Convolution enhances image recognition by dynamically reshaping CNN filters, combining biological realism with improved performance and efficiency. Credit: ...

Abstract: Image deblurring is a task with multiple real-world use cases. Convolutional Neural Network-based approaches to this task learn priors that generalize well to large-scale data. However, ...

The files JITL-RTA-TCN-DC.py and JITL-RTA-TCN-SRU.py implement a just-in-time learning method, while RTA-TCN-DC.py and RTA-TCN-SRU.py utilize the RTA-TCN method. The datasets are provided in ...