Adaptive Graph Convolution Module for Salient Object Detection
This work addresses the challenge of detecting salient objects in images for computer vision applications, representing an incremental improvement over existing multi-scale fusion methods.
The paper tackles the problem of salient object detection in complex scenes by proposing an adaptive graph convolution module (AGCM) that groups and refines prototype features using a graph architecture, resulting in dramatic quantitative and qualitative performance improvements.
Salient object detection (SOD) is a task that involves identifying and segmenting the most visually prominent object in an image. Existing solutions can accomplish this use a multi-scale feature fusion mechanism to detect the global context of an image. However, as there is no consideration of the structures in the image nor the relations between distant pixels, conventional methods cannot deal with complex scenes effectively. In this paper, we propose an adaptive graph convolution module (AGCM) to overcome these limitations. Prototype features are initially extracted from the input image using a learnable region generation layer that spatially groups features in the image. The prototype features are then refined by propagating information between them based on a graph architecture, where each feature is regarded as a node. Experimental results show that the proposed AGCM dramatically improves the SOD performance both quantitatively and quantitatively.