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

Infrared small target detection (IRSTD) has made remarkable achievements in recent years.
However, the core focus of current works lies on the philosophy of “increasing network …

Autonomous driving platforms encounter diverse driving scenarios, each with varying
hardware resources and precision requirements. Given the computational limitations of …

With the advancement of computer vision technology, the demand for fruit recognition in
agricultural automation is increasing. To improve the accuracy and efficiency of recognizing …

Accurately extracting the Region of Interest (ROI) of a palm print was crucial for subsequent
palm print recognition. However, under unconstrained environmental conditions, the user's …

At the present stage, the field of detecting vegetable pests and diseases is in dire need of
the integration of computer vision technologies. However, the deployment of efficient and …

The performance of existing lesion semantic segmentation models has shown a steady
improvement with the introduction of mechanisms like attention, skip connections, and deep …

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into
smaller ones. Prior works have explored ever more complex KD strategies involving different …

Object detection algorithms for open water aerial images present challenges such as small
object size, unsatisfactory detection accuracy, numerous network parameters, and …

Underwater object detection is highly complex and requires a high speed and accuracy. In
this paper, an underwater target detection model based on YOLOv8 (SPSM-YOLOv8) is …