Salient Object Detection: A Discriminative Regional Feature Integration Approach

Wang, Jingdong; Jiang, Huaizu; Yuan, Zejian; Cheng, Ming–Ming; Hu, Xiaowei; Zheng, Nanning

doi:10.1007/s11263-016-0977-3

Cited by 191 publications

(123 citation statements)

References 77 publications

Supporting

Mentioning

122

Contrasting

Unclassified

Order By: Relevance

“…Precisely locating the salient object regions in an image requires an understanding of both large-scale context information for the determination of object saliency, and small-scale features to localize object boundaries accurately [66]. Early approaches [3] utilize handcrafted representations of global contrast [13] or multiscale region features [53]. Li et al [29] propose one of the earliest methods that enables multi-scale deep features for salient object detection.…”

Section: Salient Object Detectionmentioning

confidence: 99%

Res2Net: A New Multi-Scale Backbone Architecture

Gao

Cheng

Zhao

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

2,231

847

View full text Add to dashboard Cite

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.

show abstract

Section: Salient Object Detectionmentioning

confidence: 99%

Res2Net: A New Multi-Scale Backbone Architecture

Gao

Cheng

Zhao

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

2,231

847

View full text Add to dashboard Cite

show abstract

“…Over the past years, some methods were proposed to detect the salient objects in an image. Early methods predicted the saliency map using a bottom-up pattern by the hand-craft feature, such as contrast [5], boundary background [57,68], center prior [24,44] and so on [22,44,51]. More details are introduced in [1,2,9].…”

Section: Related Workmentioning

confidence: 99%

“…SOD [36] contains 300 images and is proposed for image segmentation. Pixel-wise annotations of salient objects are generated by [44]. It is one of the most challenging datasets currently.…”

Section: Datasets and Evaluation Metricmentioning

confidence: 99%

EGNet: Edge Guidance Network for Salient Object Detection

Zhao

Liu

Fan

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

995

600

View full text Add to dashboard Cite

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

show abstract

“…Given the coarse masks, we employ the saliency detection model [8] to extract fine masks with detailed contours of the object. The saliency model is formed by a deep neural network trained on the MSRA-B salient object database [29]. Then, the deep neural network is fine-tuned based on the generated coarse masks of exemplars.…”

Section: Pre-augmentation Data Primingmentioning

confidence: 99%

Data Priming Network for Automatic Check-Out

Zhang

et al. 2019

Proceedings of the 27th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Automatic Check-Out (ACO) receives increased interests in recent years. An important component of the ACO system is the visual item counting, which recognizes the categories and counts of the items chosen by the customers. However, the training of such a system is challenged by the domain adaptation problem, in which the training data are images from isolated items while the testing images are for collections of items. Existing methods solve this problem with data augmentation using synthesized images, but the image synthesis leads to unreal images that affect the training process. In this paper, we propose a new data priming method to solve the domain adaptation problem. Specifically, we first use pre-augmentation data priming, in which we remove distracting background from the training images using the coarse-to-fine strategy and select images with realistic view angles by the pose pruning method. In the post-augmentation step, we train a data priming network using detection and counting collaborative learning, and select more reliable images from testing data to fine-tune the final visual item tallying network. Experiments on the large scale Retail Product Checkout (RPC) dataset demonstrate the superiority of the proposed method, i.e., we achieve 80.51% checkout accuracy compared with 56.68% of the baseline methods. The source codes can be found in https://isrc.iscas.ac.cn/gitlab/research/acm-mm-2019-ACO.

show abstract

Salient Object Detection: A Discriminative Regional Feature Integration Approach

Cited by 191 publications

References 77 publications

Res2Net: A New Multi-Scale Backbone Architecture

Res2Net: A New Multi-Scale Backbone Architecture

EGNet: Edge Guidance Network for Salient Object Detection

Data Priming Network for Automatic Check-Out

Contact Info

Product

Resources

About