1. This article belongs to the YOLOV5/YOLOV7/YOLOV8 improvement column and contains a large number of improvement methods. The improvement methods are mainly proposed based on the latest articles in 2023 and articles in 2022.
2. Provide more detailed improvement methods, such as adding attention mechanisms to different positions of the network, which facilitates experiments and can also be used as an innovation point in the paper.
3. Point increase effect: TripletAttention, a lightweight attention mechanism, achieves effective point increase!
Due to the ability of attention mechanisms to establish interdependencies between channels or spatial locations, attention mechanisms have been widely studied and applied in various computer vision tasks in recent years. In this paper, we study lightweight yet effective attention mechanisms and propose triple attention, a new method that utilizes a three-branch structure to capture cross-dimensional interactions to calculate attention weights. For an input tensor, triplet attention establishes inter-dimensional dependencies through rotation operations, followed by residual transformation, and encodes inter-channel and spatial information with negligible computational overhead. Our approach is simple and efficient and can be easily plugged into classic backbone networks as an add-on module. We demonstrate the effectiveness of our method on a variety of challenging tasks, including image classification on ImageNet-1k and object detection on the MSCOCO and PASCAL VOC datasets. Furthermore, we provide extensive insights into triple attention performance by visually inspecting GradCAM and GradCAM++ results. To us