Stacked Cross Refinement Network for Edge-Aware Salient Object Detection

Wu, Zhe; Su, Li; Huang, Qingming

doi:10.1109/iccv.2019.00736

Cited by 370 publications

(268 citation statements)

References 27 publications

Supporting

Mentioning

265

Contrasting

Unclassified

Order By: Relevance

“…Semi-supervised Inf-Net: Before training, we uniformly resize all the inputs to 352×352. We train Inf-Net using a multiscale strategy [60]. Specifically, we first re-sample the training images using different scaling ratios, i.e., {0.75, 1, 1.25}, and then train Inf-Net using the re-sampled images, which improves the generalization of our model.…”

Section: Implementation Detailsmentioning

confidence: 99%

Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images

Fan

Zhou

et al. 2020

Preprint

214

374

View full text Add to dashboard Cite

Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. Automated detection of lung infections from computed tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions from CT slices faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. To address these challenges, a novel COVID-19 Lung Infection Segmentation Deep Network (Inf-Net) is proposed to automatically identify infected regions from chest CT slices. In our Inf-Net, a parallel partial decoder is used to aggregate the high-level features and generate a global map. Then, the implicit reverse attention and explicit edge-attention are utilized to model the boundaries and enhance the representations. Moreover, to alleviate the shortage of labeled data, we present a semi-supervised segmentation framework based on a randomly selected propagation strategy, which only requires a few labeled images and leverages primarily unlabeled data. Our semi-supervised framework can improve the learning ability and achieve a higher performance. Extensive experiments on our COVID-SemiSeg and real CT volumes demonstrate that the proposed Inf-Net outperforms most cutting-edge segmentation models and advances the state-of-theart performance.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images

Fan

Zhou

et al. 2020

Preprint

214

374

View full text Add to dashboard Cite

show abstract

“…Recent deep-learning SOD models (MINet[ 161 ], SACNet[ 187 ], GateNet [ 166 ],

[ 193 ], LDF [ 148 ], DSRNet [ 164 ], EGNet [ 199 ], PoolNet [ 183 ], AFNet [ 177 ], MLMS [ 146 ], PAGE [ 44 ], CPD [ 173 ], BDPM [ 159 ], JDF [ 186 ], RAS [ 160 ], PAGR [ 180 ], C2S-Net [ 209 ], PiCANet [ 181 ], DSS [ 167 ], UCF [ 203 ], MSRNet [ 157 ], ILS [ 174 ], NLDF [ 15 ], AMULet [ 171 ], SCRN [ 162 ], BANet [ 194 ], BASNet [ 184 ], CapSal [ 147 ], DGRL [ 182 ], SRM [ 205 ]) are quantitatively evaluated using four evaluation metrics on five SOD datasets (DUTS-TE [ 174 ], DUT-OMRON [ 110 ], HKU-IS [ 154 ], ECSSD [ 103 ], Pascal-S [ 158 ]). The evaluation metrics used are maximum F-measure (

) [ 14 ], S-measure [ 224 ], E-measure [ 225 ], and mean average error (MAE) [ 106 ].…”

Section: Datasets Evaluation and Discussionmentioning

confidence: 99%

“…The learning tasks that are performed simultaneously are assumed to be related to each other. Moreover, an explicit relationship between the tasks may be defined and enforced in the model architecture [ 162 , 194 ]. As SOD leverages the knowledge contained in the other tasks and vice versa, the generalization ability of the network to unseen scenarios gets better.…”

Section: Deep Learning-based Salient Object Detectionmentioning

confidence: 99%

“…This map that represents the final prediction is supervised by the saliency GT. In Reference [ 162 ], multi-level features of SOD and edge detection are refined simultaneously through bidirectional interaction between the two tasks. To this end, individual multi-level features for each task is first extracted from the shared backbone.…”

Section: Deep Learning-based Salient Object Detectionmentioning

confidence: 99%

“…Furthermore, training and inference time for deep-learning is a challenging issue. Some recent models such as References [ 160 , 162 , 173 ] have shown a high improvement in inference time with fair prediction performance. Finally, the issues associated with acquiring huge training data, its pixel-accurate ground-truth, and more importantly keeping it from biases is a daunting task for deep learning-based models.…”

Section: Deep Learning-based Salient Object Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Salient Object Detection Techniques in Computer Vision—A Survey

Gupta

Seal

Prasad

et al. 2020

Entropy

View full text Add to dashboard Cite

Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision. The capability of automatic identification and segmentation of such salient image regions has immediate consequences for applications in the field of computer vision, computer graphics, and multimedia. A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images. These methods can be broadly categorized into two categories based on their feature engineering mechanism: conventional or deep learning-based. In this survey, most of the influential advances in image-based SOD from both conventional as well as deep learning-based categories have been reviewed in detail. Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection. Results are presented for various challenging cases for some large-scale public datasets. Different metrics considered for assessment of the performance of state-of-the-art salient object detection models are also covered. Some future directions for SOD are presented towards end.

show abstract

Dual‐branch mutual assistance network for salient object detection

Yao

Wang

2021

Int J Intell Syst

View full text Add to dashboard Cite

To maintain the boundaries of salient objects in the detection results, some methods start to apply additional edge labels to train their networks to learn detailed information. These methods have made gratifying progress. However, since the quality of the saliency maps will be affected by boundary features, it is still worth exploring how to extract effective boundary features and fuse them with semantic features. In this

show abstract

Stacked Cross Refinement Network for Edge-Aware Salient Object Detection

Cited by 370 publications

References 27 publications

Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images

Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images

Salient Object Detection Techniques in Computer Vision—A Survey

Dual‐branch mutual assistance network for salient object detection

Contact Info

Product

Resources

About