Strengthening Layer Interaction via Dynamic Layer Attention
This work addresses a specific bottleneck in network structures for researchers and practitioners in computer vision, offering an incremental improvement over existing layer attention techniques.
The paper tackled the limitation of static layer attention methods in neural networks by proposing a Dynamic Layer Attention (DLA) architecture with a Dynamic Sharing Unit (DSU) to enable dynamic context feature extraction, resulting in improved performance over state-of-the-art methods in image recognition and object detection tasks.
In recent years, employing layer attention to enhance interaction among hierarchical layers has proven to be a significant advancement in building network structures. In this paper, we delve into the distinction between layer attention and the general attention mechanism, noting that existing layer attention methods achieve layer interaction on fixed feature maps in a static manner. These static layer attention methods limit the ability for context feature extraction among layers. To restore the dynamic context representation capability of the attention mechanism, we propose a Dynamic Layer Attention (DLA) architecture. The DLA comprises dual paths, where the forward path utilizes an improved recurrent neural network block, named Dynamic Sharing Unit (DSU), for context feature extraction. The backward path updates features using these shared context representations. Finally, the attention mechanism is applied to these dynamically refreshed feature maps among layers. Experimental results demonstrate the effectiveness of the proposed DLA architecture, outperforming other state-of-the-art methods in image recognition and object detection tasks. Additionally, the DSU block has been evaluated as an efficient plugin in the proposed DLA architecture.The code is available at https://github.com/tunantu/Dynamic-Layer-Attention.