Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a micro and macro level. Specifically, at the micro level, the model should highlight all parts that belong to a certain salient object. Meanwhile, at the macro level, the model needs to discover all salient objects in a given image. To facilitate integrity learning for SOD, we design a novel Integrity Cognition Network (ICON), which explores three important components for learning strong integrity features. 1) Unlike existing models, which focus more on feature discriminability, we introduce a diverse feature aggregation (DFA) component to aggregate features with various receptive fields (i.e., kernel shape and context) and increase feature diversity. Such diversity is the foundation for mining the integral salient objects. 2) Based on the DFA features, we introduce an integrity channel enhancement (ICE) component with the goal of enhancing feature channels that highlight the integral salient objects, while suppressing the other distracting ones. 3) After extracting the enhanced features, the part-whole verification (PWV) method is employed to determine whether the part and whole object features have strong agreement. Such part-whole agreements can further improve the micro-level integrity for each salient object. To demonstrate the effectiveness of our ICON, comprehensive experiments are conducted on seven challenging benchmarks. Our ICON outperforms the baseline methods in terms of a wide range of metrics. Notably, our ICON achieves about 10% relative improvement over the previous best model in terms of average false negative ratio (FNR), on six datasets. Codes and results are available at: https://github.com/mczhuge/ICON.
翻译:虽然当前显著对象探测(SOD)工程取得了显著进展,但是在预测突出区域的完整性方面,这些工程是有限的,但是在预测突出区域的完整性方面,这些工程是有限的。 我们定义了微观和宏观一级的完整性概念。具体而言,在微观一级,模型应突出属于某一显著对象的所有部分。同时,在宏观一级,模型需要发现特定图像中的所有突出对象。2 为促进SOD的廉正学习,我们设计了一个新的完整性识别网络(ICON),它探索了学习强有力完整性特征的三个重要组成部分。1 与现有模型不同,它更侧重于特征可辨别性,我们引入了多种特性组合(DFA)的特性组合(DFA),以综合各种可接受域(e.e.,内核元形状和上下文)的特性。根据DFA的特性,我们引入了一个强化的特性系统化频道(ICE),同时抑制了其他的分流性目标。3 在提取了增强的六种特性后,我们采用的系统内部基准范围(P-hrodealalalalalal laveal ex constr ex) ex dal ex dal deal ex disal dal dal disal deal disal dal ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex exputus 10 ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex laut lauts a ex ex ex ex ex exp exfol ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex exfolutus ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex ex