scholarly journals Multiscale Deep Network with Centerness-Aware Loss for Salient Object Detection

2022 ◽  
Vol 2022 ◽  
pp. 1-14
Author(s):  
Liangliang Duan
Keyword(s):  
Object Detection ◽  
Network Architecture ◽  
State Of The Art ◽  
Saliency Detection ◽  
Salient Object Detection ◽  
Cross Entropy ◽  
Salient Object ◽  
Prediction Module ◽  
Saliency Prediction ◽  
Salient Regions

Deep encoder-decoder networks have been adopted for saliency detection and achieved state-of-the-art performance. However, most existing saliency models usually fail to detect very small salient objects. In this paper, we propose a multitask architecture, M2Net, and a novel centerness-aware loss for salient object detection. The proposed M2Net aims to solve saliency prediction and centerness prediction simultaneously. Specifically, the network architecture is composed of a bottom-up encoder module, top-down decoder module, and centerness prediction module. In addition, different from binary cross entropy, the proposed centerness-aware loss can guide the proposed M2Net to uniformly highlight the entire salient regions with well-defined object boundaries. Experimental results on five benchmark saliency datasets demonstrate that M2Net outperforms state-of-the-art methods on different evaluation metrics.

scholarly journals Revise-Net: Exploiting Reverse Attention Mechanism for Salient Object Detection

2021 ◽  
Vol 13 (23) ◽  
pp. 4941
Author(s):  
Rukhshanda Hussain ◽  
Yash Karbhari ◽  
Muhammad Fazal Ijaz ◽  
Marcin Woźniak ◽  
Pawan Kumar Singh ◽  
...  
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Similarity Index ◽  
Saliency Map ◽  
Salient Object Detection ◽  
Semantic Features ◽  
Salient Object ◽  
Fully Convolutional Neural Networks ◽  
Boundary Estimation ◽  
Prediction Module

Recently, deep learning-based methods, especially utilizing fully convolutional neural networks, have shown extraordinary performance in salient object detection. Despite its success, the clean boundary detection of the saliency objects is still a challenging task. Most of the contemporary methods focus on exclusive edge detection modules in order to avoid noisy boundaries. In this work, we propose leveraging on the extraction of finer semantic features from multiple encoding layers and attentively re-utilize it in the generation of the final segmentation result. The proposed Revise-Net model is divided into three parts: (a) the prediction module, (b) a residual enhancement module, and (c) reverse attention modules. Firstly, we generate the coarse saliency map through the prediction modules, which are fine-tuned in the enhancement module. Finally, multiple reverse attention modules at varying scales are cascaded between the two networks to guide the prediction module by employing the intermediate segmentation maps generated at each downsampling level of the REM. Our method efficiently classifies the boundary pixels using a combination of binary cross-entropy, similarity index, and intersection over union losses at the pixel, patch, and map levels, thereby effectively segmenting the saliency objects in an image. In comparison with several state-of-the-art frameworks, our proposed Revise-Net model outperforms them with a significant margin on three publicly available datasets, DUTS-TE, ECSSD, and HKU-IS, both on regional and boundary estimation measures.

scholarly journals Deep Embedding Features for Salient Object Detection

2019 ◽  
Vol 33 ◽  
pp. 9340-9347 ◽  
Author(s):  
Yunzhi Zhuge ◽  
Yu Zeng ◽  
Huchuan Lu
Keyword(s):  
Object Detection ◽  
Rapid Development ◽  
Saliency Detection ◽  
Salient Object Detection ◽  
Detection Methods ◽  
Salient Object ◽  
Novel Approach ◽  
Deep Embedding ◽  
Salient Regions ◽  
Multi Level

Benefiting from the rapid development of Convolutional Neural Networks (CNNs), some salient object detection methods have achieved remarkable results by utilizing multi-level convolutional features. However, the saliency training datasets is of limited scale due to the high cost of pixel-level labeling, which leads to a limited generalization of the trained model on new scenarios during testing. Besides, some FCN-based methods directly integrate multi-level features, ignoring the fact that the noise in some features are harmful to saliency detection. In this paper, we propose a novel approach that transforms prior information into an embedding space to select attentive features and filter out outliers for salient object detection. Our network firstly generates a coarse prediction map through an encorder-decorder structure. Then a Feature Embedding Network (FEN) is trained to embed each pixel of the coarse map into a metric space, which incorporates much attentive features that highlight salient regions and suppress the response of non-salient regions. Further, the embedded features are refined through a deep-to-shallow Recursive Feature Integration Network (RFIN) to improve the details of prediction maps. Moreover, to alleviate the blurred boundaries, we propose a Guided Filter Refinement Network (GFRN) to jointly optimize the predicted results and the learnable guidance maps. Extensive experiments on five benchmark datasets demonstrate that our method outperforms state-of-the-art results. Our proposed method is end-to-end and achieves a realtime speed of 38 FPS.

Saliency detection in deep learning era: trends of development

2019 ◽  
pp. 10-36 ◽  
Author(s):  
M. N. Favorskaya ◽  
L. C. Jain
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Event Detection ◽  
Visual Analysis ◽  
Saliency Detection ◽  
Salient Object Detection ◽  
Public Image ◽  
Detection Methods ◽  
Salient Object ◽  
Salient Event

Introduction:Saliency detection is a fundamental task of computer vision. Its ultimate aim is to localize the objects of interest that grab human visual attention with respect to the rest of the image. A great variety of saliency models based on different approaches was developed since 1990s. In recent years, the saliency detection has become one of actively studied topic in the theory of Convolutional Neural Network (CNN). Many original decisions using CNNs were proposed for salient object detection and, even, event detection.Purpose:A detailed survey of saliency detection methods in deep learning era allows to understand the current possibilities of CNN approach for visual analysis conducted by the human eyes’ tracking and digital image processing.Results:A survey reflects the recent advances in saliency detection using CNNs. Different models available in literature, such as static and dynamic 2D CNNs for salient object detection and 3D CNNs for salient event detection are discussed in the chronological order. It is worth noting that automatic salient event detection in durable videos became possible using the recently appeared 3D CNN combining with 2D CNN for salient audio detection. Also in this article, we have presented a short description of public image and video datasets with annotated salient objects or events, as well as the often used metrics for the results’ evaluation.Practical relevance:This survey is considered as a contribution in the study of rapidly developed deep learning methods with respect to the saliency detection in the images and videos.

scholarly journals SuperVAE: Superpixelwise Variational Autoencoder for Salient Object Detection

2019 ◽  
Vol 33 ◽  
pp. 8569-8576 ◽  
Author(s):  
Bo Li ◽  
Zhengxing Sun ◽  
Yuqi Guo
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Saliency Detection ◽  
Salient Object Detection ◽  
Salient Object ◽  
Image Saliency ◽  
Spatial Consistency ◽  
Variational Autoencoder ◽  
Benchmark Datasets ◽  
Supervised Methods

Image saliency detection has recently witnessed rapid progress due to deep neural networks. However, there still exist many important problems in the existing deep learning based methods. Pixel-wise convolutional neural network (CNN) methods suffer from blurry boundaries due to the convolutional and pooling operations. While region-based deep learning methods lack spatial consistency since they deal with each region independently. In this paper, we propose a novel salient object detection framework using a superpixelwise variational autoencoder (SuperVAE) network. We first use VAE to model the image background and then separate salient objects from the background through the reconstruction residuals. To better capture semantic and spatial contexts information, we also propose a perceptual loss to take advantage from deep pre-trained CNNs to train our SuperVAE network. Without the supervision of mask-level annotated data, our method generates high quality saliency results which can better preserve object boundaries and maintain the spatial consistency. Extensive experiments on five wildly-used benchmark datasets show that the proposed method achieves superior or competitive performance compared to other algorithms including the very recent state-of-the-art supervised methods.

Double Feature Combination: Region Contrast for Visual Salient Object Detection

2012 ◽  
Vol 239-240 ◽  
pp. 811-815
Author(s):  
Zhi Hai Sun ◽  
Teng Song ◽  
Wen Hui Zhou ◽  
Hua Zhang
Keyword(s):  
Object Detection ◽  
Saliency Detection ◽  
Visual Saliency ◽  
Recall Rate ◽  
Detection Algorithm ◽  
Salient Object Detection ◽  
Color Contrast ◽  
Salient Object ◽  
Histograms Of Oriented Gradients ◽  
Visual Saliency Detection

Visual saliency detection has become an important step between computer vision and digital image processing. Recent methods almost form a computational model based on color, which are difficult to overcome the shortcoming with cluttered and textured background. This paper proposes a novel salient object detection algorithm integrating with region color contrast and histograms of oriented gradients (HoG). Extensively experiments show that our algorithm outperforms other state-of-art saliency methods, yielding higher precision and better recall rate, even lower mean absolution error.

scholarly journals Salient Object Detection with Semantic Priors

2017 ◽  
Author(s):  
Tam V. Nguyen ◽  
Luoqi Liu
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Saliency Map ◽  
Salient Object Detection ◽  
Salient Object ◽  
Artificial Intelligence Research ◽  
Semantic Map ◽  
Regional Features ◽  
Computational Sciences

Salient object detection has increasingly become a popular topic in cognitive and computational sciences, including computer vision and artificial intelligence research. In this paper, we propose integrating semantic priors into the salient object detection process. Our algorithm consists of three basic steps. Firstly, the explicit saliency map is obtained based on the semantic segmentation refined by the explicit saliency priors learned from the data. Next, the implicit saliency map is computed based on a trained model which maps the implicit saliency priors embedded into regional features with the saliency values. Finally, the explicit semantic map and the implicit map are adaptively fused to form a pixel-accurate saliency map which uniformly covers the objects of interest. We further evaluate the proposed framework on two challenging datasets, namely, ECSSD and HKUIS. The extensive experimental results demonstrate that our method outperforms other state-of-the-art methods.

scholarly journals Semantic-Guided Attention Refinement Network for Salient Object Detection in Optical Remote Sensing Images

2021 ◽  
Vol 13 (11) ◽  
pp. 2163
Author(s):  
Zhou Huang ◽  
Huaixin Chen ◽  
Biyuan Liu ◽  
Zhixi Wang
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Network Architecture ◽  
Salient Object Detection ◽  
Optical Remote Sensing ◽  
Salient Object ◽  
Remote Sensing Images ◽  
Multi Level ◽  
Object Area ◽  
High Level

Although remarkable progress has been made in salient object detection (SOD) in natural scene images (NSI), the SOD of optical remote sensing images (RSI) still faces significant challenges due to various spatial resolutions, cluttered backgrounds, and complex imaging conditions, mainly for two reasons: (1) accurate location of salient objects; and (2) subtle boundaries of salient objects. This paper explores the inherent properties of multi-level features to develop a novel semantic-guided attention refinement network (SARNet) for SOD of NSI. Specifically, the proposed semantic guided decoder (SGD) roughly but accurately locates the multi-scale object by aggregating multiple high-level features, and then this global semantic information guides the integration of subsequent features in a step-by-step feedback manner to make full use of deep multi-level features. Simultaneously, the proposed parallel attention fusion (PAF) module combines cross-level features and semantic-guided information to refine the object’s boundary and highlight the entire object area gradually. Finally, the proposed network architecture is trained through an end-to-end fully supervised model. Quantitative and qualitative evaluations on two public RSI datasets and additional NSI datasets across five metrics show that our SARNet is superior to 14 state-of-the-art (SOTA) methods without any post-processing.

scholarly journals Hybrid Local and Global Deep-Learning Architecture for Salient-Object Detection

2020 ◽  
Vol 10 (23) ◽  
pp. 8754
Author(s):  
Wajeeha Sultan ◽  
Nadeem Anjum ◽  
Mark Stansfield ◽  
Naeem Ramzan
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
State Of The Art ◽  
Salient Object Detection ◽  
Salient Object ◽  
Global Level ◽  
Low Contrast ◽  
Qualitative And Quantitative ◽  
Exact Boundary ◽  
Quantitative Analyses

Salient-object detection is a fundamental and the most challenging problem in computer vision. This paper focuses on the detection of salient objects, especially in low-contrast images. To this end, a hybrid deep-learning architecture is proposed where features are extracted on both the local and global level. These features are then integrated to extract the exact boundary of the object of interest in an image. Experimentation was performed on five standard datasets, and results were compared with state-of-the-art approaches. Both qualitative and quantitative analyses showed the robustness of the proposed architecture.

scholarly journals Hybrid-Attention Network for RGB-D Salient Object Detection

2020 ◽  
Vol 10 (17) ◽  
pp. 5806 ◽  
Author(s):  
Yuzhen Chen ◽  
Wujie Zhou
Keyword(s):  
Object Detection ◽  
Salient Object Detection ◽  
Depth Information ◽  
Salient Object ◽  
Depth Sensor ◽  
Attention Network ◽  
Depth Maps ◽  
Saliency Prediction ◽  
Ablation Study ◽  
High Level

Depth information has been widely used to improve RGB-D salient object detection by extracting attention maps to determine the position information of objects in an image. However, non-salient objects may be close to the depth sensor and present high pixel intensities in the depth maps. This situation in depth maps inevitably leads to erroneously emphasize non-salient areas and may have a negative impact on the saliency results. To mitigate this problem, we propose a hybrid attention neural network that fuses middle- and high-level RGB features with depth features to generate a hybrid attention map to remove background information. The proposed network extracts multilevel features from RGB images using the Res2Net architecture and then integrates high-level features from depth maps using the Inception-v4-ResNet2 architecture. The mixed high-level RGB features and depth features generate the hybrid attention map, which is then multiplied to the low-level RGB features. After decoding by several convolutions and upsampling, we obtain the final saliency prediction, achieving state-of-the-art performance on the NJUD and NLPR datasets. Moreover, the proposed network has good generalization ability compared with other methods. An ablation study demonstrates that the proposed network effectively performs saliency prediction even when non-salient objects interfere detection. In fact, after removing the branch with high-level RGB features, the RGB attention map that guides the network for saliency prediction is lost, and all the performance measures decline. The resulting prediction map from the ablation study shows the effect of non-salient objects close to the depth sensor. This effect is not present when using the complete hybrid attention network. Therefore, RGB information can correct and supplement depth information, and the corresponding hybrid attention map is more robust than using a conventional attention map constructed only with depth information.

scholarly journals Detecting Salient Image Objects Using Color Histogram Clustering for Region Granularity

2021 ◽  
Vol 7 (9) ◽  
pp. 187
Author(s):  
Seena Joseph ◽  
Oludayo O. Olugbara
Keyword(s):  
Object Detection ◽  
Saliency Detection ◽  
Contrast Ratio ◽  
Salient Object Detection ◽  
Color Images ◽  
Color Histogram ◽  
Detection Methods ◽  
Color Contrast ◽  
Salient Object ◽  
Selection Of

Salient object detection represents a novel preprocessing stage of many practical image applications in the discipline of computer vision. Saliency detection is generally a complex process to copycat the human vision system in the processing of color images. It is a convoluted process because of the existence of countless properties inherent in color images that can hamper performance. Due to diversified color image properties, a method that is appropriate for one category of images may not necessarily be suitable for others. The selection of image abstraction is a decisive preprocessing step in saliency computation and region-based image abstraction has become popular because of its computational efficiency and robustness. However, the performances of the existing region-based salient object detection methods are extremely hooked on the selection of an optimal region granularity. The incorrect selection of region granularity is potentially prone to under- or over-segmentation of color images, which can lead to a non-uniform highlighting of salient objects. In this study, the method of color histogram clustering was utilized to automatically determine suitable homogenous regions in an image. Region saliency score was computed as a function of color contrast, contrast ratio, spatial feature, and center prior. Morphological operations were ultimately performed to eliminate the undesirable artifacts that may be present at the saliency detection stage. Thus, we have introduced a novel, simple, robust, and computationally efficient color histogram clustering method that agglutinates color contrast, contrast ratio, spatial feature, and center prior for detecting salient objects in color images. Experimental validation with different categories of images selected from eight benchmarked corpora has indicated that the proposed method outperforms 30 bottom-up non-deep learning and seven top-down deep learning salient object detection methods based on the standard performance metrics.

Sign in / Sign up

Export Citation Format

Share Document