国际人工智能顶级会议AAAI-2021（AAAI Conference on Artificial Intelligence 2021）于2021年2月2日—9日召开。我院梁荣华教授团队徐斌伟（2020级博士生）、梁浩然（通讯作者）、梁荣华、陈朋在显著性目标检测方向的论文“Locate Globally, Segment Locally: A Progressive Architecture With Knowledge Review Network for Salient Object Detection”在会上发表。该文模拟人类全局定位显著性目标然后精确分割的过程，提出了一种新型的基于知识回顾网络的渐进式结构用于显著性目标检测，并在多个具有挑战的数据集上取得了最先进的效果。

AAAI Conference on Artificial Intelligence (AAAI)始于1987年，今年已是第35届，是人工智能领域的最顶级会议，由国际人工智能协会主办，在中国计算机学会（CCF）期刊会议推荐列表中为A类。AAAI2021录用率约为21%，以线上VR方式召开。本次AAAI会议的论文录用见证了我院在人工智能领域所取得的可喜进展。

附：

题目：Locate Globally, Segment Locally: A Progressive Architecture With Knowledge Review Network for Salient Object Detection

作者：Binwei Xu, Haoran Liang*, Ronghua Liang, Peng Chen

Abstract

Salient object location and segmentation are two different tasks in salient object detection (SOD). The former aims to globally find the most attractive objects in image, whereas the latter can be achieved only using local regions that contain salient objects. However, previous methods mainly accomplish the two tasks simultaneously in a simple end-to-end manner, which leads to the ignorance of the differences between them. We assume that the human vision system orderly locates and segments object, so we propose a novel progressive architecture with knowledge review network (PA-KRN) for SOD. It consists of three parts. (1) A coarse locating module (CLM) that uses body-attention label locates rough areas containing salient objects without boundary details. (2) An attention-based sampler highlights salient object regions with high resolution based on body-attention maps. (3) A fine segmenting module (FSM) finely segments salient objects. The networks applied in CLM and FSM are mainly based on our proposed knowledge review network (KRN) that utilizes the finest feature maps to reintegrate all previous layers, which can make up for the important information that is continuously diluted in the top-down path. Experiments on five benchmarks demonstrate that our single KRN can outperform state-of-the-art methods. Furthermore, our PA-KRN performs better and substantially surpasses the aforementioned methods.