Lee, Yongwoo Lee, Minhyeok Cho, Suhwan Lee, Sangyoun 2024-04-24T07:40:45Z 2024-04-24T07:40:45Z 2024-03-07 2023-10 https://pubs.kist.re.kr/handle/201004/149718 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 using 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. English IEEE Adaptive Graph Convolution Module for Salient Object Detection Conference 10.1109/ICIP49359.2023.10222238 1 30th IEEE International Conference on Image Processing (ICIP), pp.1395 - 1399 30th IEEE International Conference on Image Processing (ICIP) 1395 1399 US Kuala Lumpur, MALAYSIA 2023-10-08 2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 001106821001095 2-s2.0-85180772231