The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …

Fine-tuning visual models has been widely shown promising performance on many
downstream visual tasks. With the surprising development of pre-trained visual foundation …

In the past years, YOLO-series models have emerged as the leading approaches in the area
of real-time object detection. Many studies pushed up the baseline to a higher level by …

For years, the YOLO series has been the de facto industry-level standard for efficient object
detection. The YOLO community has prospered overwhelmingly to enrich its use in a …

At the heart of foundation models is the philosophy of" more is different", exemplified by the
astonishing success in computer vision and natural language processing. However, the …

Abstract Knowledge distillation has been applied to image classification successfully.
However, object detection is much more sophisticated and most knowledge distillation …

Abstract Knowledge distillation has been applied to various tasks successfully. The current
distillation algorithm usually improves students' performance by imitating the output of the …

Abstract Knowledge distillation (KD) has proven to be a highly effective approach for
enhancing model performance through a teacher-student training scheme. However, most …

The representation gap between teacher and student is an emerging topic in knowledge
distillation (KD). To reduce the gap and improve the performance, current methods often …

Transformer-based trackers have achieved strong accuracy on the standard benchmarks.
However, their efficiency remains an obstacle to practical deployment on both GPU and …