Saliency detection is one of the most challenging problems in image analysis and computer vision. Many approaches propose different architectures based on the psychological and biological properties of the human visual attention system. However, there is still no abstract framework that summarizes the existing methods. In this paper, we offered a general framework for saliency models, which consists of five main steps: pre-processing, feature extraction, saliency map generation, saliency map combination, and post-processing. Also, we study different saliency models containing each level and compare their performance. This framework helps researchers to have a comprehensive view of studying new methods.

Fully convolutional neural networks (FCNs) have shown their advantages in the salient object detection task. However, most existing FCNs-based methods still suffer from coarse object boundaries. In this paper, to solve this problem, we focus on the complementarity between salient edge information and salient object information. Accordingly, we present an edge guidance network (EGNet) for salient object detection with three steps to simultaneously model these two kinds of complementary information in a single network. In the first step, we extract the salient object features by a progressive fusion way. In the second step, we integrate the local edge information and global location information to obtain the salient edge features. Finally, to sufficiently leverage these complementary features, we couple the same salient edge features with salient object features at various resolutions. Benefiting from the rich edge information and location information in salient edge features, the fused features can help locate salient objects, especially their boundaries more accurately. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on six widely used datasets without any pre-processing and post-processing. The source code is available at http: //mmcheng.net/egnet/.

Recent progress on salient object detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs). Semantic segmentation and salient object detection algorithms developed lately have been mostly based on Fully Convolutional Neural Networks (FCNs). There is still a large room for improvement over the generic FCN models that do not explicitly deal with the scale-space problem. Holistically-Nested Edge Detector (HED) provides a skip-layer structure with deep supervision for edge and boundary detection, but the performance gain of HED on saliency detection is not obvious. In this paper, we propose a new salient object detection method by introducing short connections to the skip-layer structures within the HED architecture. Our framework takes full advantage of multi-level and multi-scale features extracted from FCNs, providing more advanced representations at each layer, a property that is critically needed to perform segment detection. Our method produces state-of-theart results on 5 widely tested salient object detection benchmarks, with advantages in terms of efficiency (0.08 seconds per image), effectiveness, and simplicity over the existing algorithms. Beyond that, we conduct an exhaustive analysis on the role of training data on performance. Our experimental results provide a more reasonable and powerful training set for future research and fair comparisons.

显着对象检测（SOD）在图像分析中具有若干应用。基于深度学习的SOD方法是最有效的，但它们可能会错过具有相似颜色的前景部分。为了规避问题，我们介绍了一个后处理方法，名为\ Texit {SuperPixel Materionity}（Sess）的后期处理方法，其交替地执行两个操作，以便显着完成：基于对象的SuperPixel分段和基于SuperPixel的显着性估算。 Sess使用输入显着图来估算超像素描绘的种子，并在前景和背景中定义超顶盒查询。新的显着性图是由查询和超像素之间的颜色相似性产生的。对于给定数量的迭代的过程重复，使得所有产生的显着性图通过蜂窝自动机组合成单个。最后，使用其平均值合并后处理和初始映射。我们展示SES可以始终如一地，并在五个图像数据集上一致而大大提高三种基于深度学习的SOD方法的结果。

Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pretrained convolutional neural networks (CNNs). Compared to high-level features, low-level features contribute less to performance but cost more computations because of their larger spatial resolutions. In this paper, we propose a novel Cascaded Partial Decoder (CPD) framework for fast and accurate salient object detection. On the one hand, the framework constructs partial decoder which discards larger resolution features of shallower layers for acceleration. On the other hand, we observe that integrating features of deeper layers obtain relatively precise saliency map. Therefore we directly utilize generated saliency map to refine the features of backbone network. This strategy efficiently suppresses distractors in the features and significantly improves their representation ability. Experiments conducted on five benchmark datasets exhibit that the proposed model not only achieves state-of-the-art performance but also runs much faster than existing models. Besides, the proposed framework is further applied to improve existing multi-level feature aggregation models and significantly improve their efficiency and accuracy.

We solve the problem of salient object detection by investigating how to expand the role of pooling in convolutional neural networks. Based on the U-shape architecture, we first build a global guidance module (GGM) upon the bottom-up pathway, aiming at providing layers at different feature levels the location information of potential salient objects. We further design a feature aggregation module (FAM) to make the coarse-level semantic information well fused with the fine-level features from the top-down pathway. By adding FAMs after the fusion operations in the topdown pathway, coarse-level features from the GGM can be seamlessly merged with features at various scales. These two pooling-based modules allow the high-level semantic features to be progressively refined, yielding detail enriched saliency maps. Experiment results show that our proposed approach can more accurately locate the salient objects with sharpened details and hence substantially improve the performance compared to the previous state-of-the-arts. Our approach is fast as well and can run at a speed of more than 30 FPS when processing a 300 × 400 image. Code can be found at http://mmcheng.net/poolnet/.

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles which combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy and optimization function, etc. In this paper, we provide a review on deep learning based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely Convolutional Neural Network (CNN). Then we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network based learning systems.

无监督的突出物体检测（USOD）对于工业应用和下游任务来说是最重要的意义。基于深度学习（DL）的USOD方法利用多种传统的SOD方法提取的一些低质量的显着性预测，作为显着性提示，主要捕获图像中的一些显着区域。此外，它们通过语义信息的助手优化这些显着性提示，该显着性提示是由其他相关视觉任务中的监督学习训练的一些型号获得的。在这项工作中，我们提出了一种两级激活 - 到显着性（A2S）框架，有效地产生了高质量的显着性提示，并使用这些提示培训强大的耐药性检测器。更重要的是，在整个培训过程中没有人类注释参与我们的框架。在第一阶段中，我们将普雷托网络（MOCO V2）转换为将多级别特征聚合到单个激活图，其中提出了一种自适应决策边界（ADB）来帮助训练变换网络。为了便于生成高质量的伪标签，我们提出了一种损失功能来扩大像素之间的特征距离及其手段。在第二阶段，在线标签纠正（OLR）策略在培训过程中更新伪标签，以减少分散的人的负面影响。此外，我们使用两个残余注意模块（RAM）来构造轻量级显着探测器，其使用低级功能中的互补信息，例如边缘和颜色，从而优化高级功能。对几个SOD基准的广泛实验证明，与现有的USOD方法相比，我们的框架报告了显着性能。此外，在3000张图像上培训我们的框架约1小时，比以前的最先进的方法快30倍。

Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality. In this paper, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement. The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy -pixel-, patch-and map-level -by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersectionover-Union (IoU) losses. Equipped with the hybrid loss, the proposed predict-refine architecture is able to effectively segment the salient object regions and accurately predict the fine structures with clear boundaries. Experimental results on six public datasets show that our method outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures. Our method runs at over 25 fps on a single GPU. The code is available at: https://github.com/NathanUA/BASNet.

尽管当前的显着对象检测（SOD）作品已经取得了重大进展，但在预测的显着区域的完整性方面，它们受到限制。我们在微观和宏观水平上定义了完整性的概念。具体而言，在微观层面上，该模型应突出显示属于某个显着对象的所有部分。同时，在宏观层面上，模型需要在给定图像中发现所有显着对象。为了促进SOD的完整性学习，我们设计了一个新颖的完整性认知网络（ICON），该网络探讨了学习强大完整性特征的三个重要组成部分。 1）与现有模型不同，该模型更多地集中在功能可区分性上，我们引入了各种功能集合（DFA）组件，以汇总具有各种接受场（即内核形状和背景）的特征，并增加了功能多样性。这种多样性是挖掘积分显着物体的基础。 2）基于DFA功能，我们引入了一个完整性通道增强（ICE）组件，其目标是增强功能通道，以突出积分显着对象，同时抑制其他分心的对象。 3）提取增强功能后，采用零件整体验证（PWV）方法来确定零件和整个对象特征是否具有很强的一致性。这样的部分协议可以进一步改善每个显着对象的微观完整性。为了证明我们图标的有效性，对七个具有挑战性的基准进行了全面的实验。我们的图标在广泛的指标方面优于基线方法。值得注意的是，我们的图标在六个数据集上的平均假阴影（FNR）（FNR）方面，相对于以前的最佳模型的相对改善约为10％。代码和结果可在以下网址获得：https：//github.com/mczhuge/icon。

显着对象检测（SOD）模拟了人类视觉感知系统以在场景中定位最具吸引力的对象，已广泛应用于各种计算机视觉任务。现在，随着深度传感器的出现，可以轻松捕获具有富裕的空间信息的深度图，并有利于提高SOD的性能。尽管在过去几年中提出了各种具有有前途的性能的基于RGB-D的SOD模型，但仍缺乏对这些主题的这些模型和挑战的深入了解。在本文中，我们从各个角度提供了基于RGB-D的SOD模型的全面调查，并详细介绍了相关的基准数据集。此外，考虑到光场还可以提供深度图，我们还从该域中回顾了SOD模型和流行的基准数据集。此外，为了研究现有模型的SOD能力，我们进行了全面的评估，以及基于属性的几种基于RGB-D的SOD模型的评估。最后，我们讨论了基于RGB-D的SOD的几个挑战和开放方向，以供未来的研究。将在https://github.com/taozh2017/rgbdsodsurvey上公开提供所有收集的模型，基准数据集，源代码链接，用于基于属性的评估的数据集以及评估代码

Semantic segmentation classifies each pixel in the image. Due to its advantages, semantic segmentation is used in many tasks, such as cancer detection, robot-assisted surgery, satellite image analysis, and self-driving cars. Accuracy and efficiency are the two crucial goals for this purpose, and several state-of-the-art neural networks exist. By employing different techniques, new solutions have been presented in each method to increase efficiency and accuracy and reduce costs. However, the diversity of the implemented approaches for semantic segmentation makes it difficult for researchers to achieve a comprehensive view of the field. In this paper, an abstraction model for semantic segmentation offers a comprehensive view of the field. The proposed framework consists of four general blocks that cover the operation of the majority of semantic segmentation methods. We also compare different approaches and analyze each of the four abstraction blocks' importance in each method's operation.

本文通过控制功能级别的RGB图像和深度图之间的消息，介绍了RGB-D显着对象检测的新型深神经网络框架，并探索有关RGB和深度特征的远程语义上下文和几何信息推断出明显的对象。为了实现这一目标，我们通过图神经网络和可变形的卷积制定动态消息传播（DMP）模块，以动态学习上下文信息，并自动预测消息传播控制的过滤权重和亲和力矩阵。我们将该模块进一步嵌入基于暹罗的网络中，分别处理RGB图像和深度图，并设计多级特征融合（MFF）模块，以探索精制的RGB和深度特征之间的跨级信息。与六个基准数据集上用于RGB-D显着对象检测的17种最先进的方法相比，实验结果表明，我们的方法在定量和视觉上都优于其他所有方法。

使用变压器 - 卷积神经网络（CNN）的视觉显着性预测具有显着的高级计算模型，以实现显着性预测。但是，准确模拟人类皮层中视觉注意的机制仍然是一个学术挑战。将人类视力的属性集成到CNN体系结构的设计中，这是至关重要的，从而导致感知上更相关的显着性预测。由于CNN体系结构的固有归纳偏见，因此缺乏足够的长距离上下文编码能力。这阻碍了基于CNN的显着性模型，无法捕获模仿人类观看行为的属性。通过利用自我发项机制来编码远程信息，变形金刚在编码远程信息方面表现出了巨大潜力。在本文中，我们提出了一个新颖的显着性模型，该模型将变压器组件集成到CNNs以捕获远程上下文视觉信息。实验结果表明，变压器为显着性预测提供了附加的价值，从而增强了其在性能中的感知相关性。我们提出的使用变压器的显着性模型在公共基准和显着性预测模型的竞争上取得了卓越的成果。我们提出的显着模型TransAlnet的源代码可在以下网址获得：https：//github.com/ljovo/transalnet

由于透明玻璃与图像中的任意物体相同，大多数现有物体检测方法产生较差的玻璃检测结果。与众不同的基于深度学习的智慧不同，只需使用对象边界作为辅助监督，我们利用标签解耦将原始标记的地图（GT）映射分解为内部扩散图和边界扩散图。与两个新生成的地图合作的GT映射破坏了物体边界的不平衡分布，导致玻璃检测质量改善。我们有三个关键贡献来解决透明的玻璃探测问题：（1）我们提出了一个三流神经网络（短暂的呼叫GlassNet），完全吸收三张地图中的有益功能。 （2）我们设计多尺度交互扩张模块，以探索更广泛的上下文信息。 （3）我们开发了一个基于关注的边界意识的功能拼接模块，用于集成多模态信息。基准数据集的广泛实验表明，在整体玻璃检测精度和边界清晰度方面，在SOTA方面对我们的方法进行了明确的改进。

玻璃在我们的日常生活中非常普遍。现有的计算机视觉系统忽略了它，因此可能会产生严重的后果，例如，机器人可能会坠入玻璃墙。但是，感知玻璃的存在并不简单。关键的挑战是，任意物体/场景可以出现在玻璃后面。在本文中，我们提出了一个重要的问题，即从单个RGB图像中检测玻璃表面。为了解决这个问题，我们构建了第一个大规模玻璃检测数据集（GDD），并提出了一个名为GDNet-B的新颖玻璃检测网络，该网络通过新颖的大型场探索大型视野中的丰富上下文提示上下文特征集成（LCFI）模块并将高级和低级边界特征与边界特征增强（BFE）模块集成在一起。广泛的实验表明，我们的GDNET-B可以在GDD测试集内外的图像上达到满足玻璃检测结果。我们通过将其应用于其他视觉任务（包括镜像分割和显着对象检测）来进一步验证我们提出的GDNET-B的有效性和概括能力。最后，我们显示了玻璃检测的潜在应用，并讨论了可能的未来研究方向。

由于规模和形状的极端复杂性以及预测位置的不确定性，光学遥感图像（RSI-SOD）中的显着对象检测是一项非常困难的任务。现有的SOD方法可以满足自然场景图像的检测性能，但是由于遥感图像中上述图像特性，它们不能很好地适应RSI-SOD。在本文中，我们为光学RSIS中的SOD提出了一个新颖的注意力指导网络（AGNET），包括位置增强阶段和细节细节阶段。具体而言，位置增强阶段由语义注意模块和上下文注意模块组成，以准确描述显着对象的大致位置。细节完善阶段使用提出的自我注册模块在注意力的指导下逐步完善预测结果并逆转注意力。此外，混合损失用于监督网络的培训，这可以从像素，区域和统计数据的三个角度来改善模型的性能。在两个流行的基准上进行的广泛实验表明，与其他最先进的方法相比，AGNET可以达到竞争性能。该代码将在https://github.com/nuaayh/agnet上找到。

光场显着性检测 - 由于许多视力任务中的效用，重要 - 仍然缺乏速度，可以提高准确性。由于在光场中的显着性检测问题作为分割任务或记忆任务，现有方法消耗不必要的大量计算资源进行培训，并且具有更长的测试时间进行测试。我们通过积极地将大型光场图像减少到适当的三声道特征映射的大量三声道特征映射来解决这一点，适合使用RGB图像显着检测器具有注意机制。我们通过引入新的卷积神经网络的特征提取和编码模块来实现这一目标。我们的显着探测器需要0.4美元来处理CPU的9 \ Times9 \ Times512 \ Times375 $的灯田。比最先进的灯场显着性检测器更快，精度更快。此外，与最先进的灯场显着性检测器相比，我们的架构的模型大小显着降低。我们的工作表明，通过侵略性尺寸减小从轻场提取特征，引起注意机构导致较快，准确的光场显着探测器，导致近实时光场处理。

突出对象检测在许多下游任务中发挥着重要作用。然而，复杂的现实世界场景具有不同尺度和突出对象的数量仍然构成挑战。在本文中，我们直接解决了在复杂场景中检测多个突出对象的问题。我们提出了一种在空间和频道空间中的非本地特征信息的网络架构，捕获单独对象之间的远程依赖性。传统的自下而上和非本地特征与特征融合门中的边缘特性相结合，逐渐改进解码器中的突出物体预测。我们表明，即使在复杂的情况下，我们的方法也可以准确地定位多个突出区域。为了证明我们对多个突出对象问题的方法的功效，我们策划仅包含多个突出对象的新数据集。我们的实验证明了所提出的方法在没有任何预处理和后处理的情况下展示了五种广泛使用的数据集的最新结果。我们在我们的多对象数据集中获得了对竞争技术的进一步绩效改进。数据集和源代码是可用的：https://github.com/ericdengbowen/dslrdnet。

现有的突出实例检测（SID）方法通常从像素级注释数据集中学习。在本文中，我们向SID问题提出了第一个弱监督的方法。虽然在一般显着性检测中考虑了弱监管，但它主要基于使用类标签进行对象本地化。然而，仅使用类标签来学习实例知识的显着性信息是不普遍的，因为标签可能不容易地分离具有高语义亲和力的显着实例。由于子化信息提供了对突出项的数量的即时判断，因此自然地与检测突出实例相关，并且可以帮助分离相同实例的不同部分的同一类别的单独实例。灵感来自这一观察，我们建议使用课程和镇展标签作为SID问题的弱监督。我们提出了一种具有三个分支的新型弱监管网络：显着性检测分支利用类一致性信息来定位候选物体;边界检测分支利用类差异信息来解除对象边界;和Firedroid检测分支，使用子化信息来检测SALICE实例质心。然后融合该互补信息以产生突出的实例图。为方便学习过程，我们进一步提出了一种渐进的培训方案，以减少标签噪声和模型中学到的相应噪声，通过往复式突出实例预测和模型刷新模型。我们广泛的评估表明，该方法对精心设计的基线方法进行了有利地竞争，这些方法适应了相关任务。