Cascaded Partial Decoder for Fast and Accurate Salient Object Detection

@article{Wu2019CascadedPD,
  title={Cascaded Partial Decoder for Fast and Accurate Salient Object Detection},
  author={Zhe Wu and Li Su and Qingming Huang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={3902-3911}
}
  • Zhe Wu, Li Su, Qingming Huang
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pre-trained convolutional neural networks (CNNs. [...] Key Method On the one hand, the framework constructs partial decoder which discards larger resolution features of shallow layers for acceleration. On the other hand, we observe that integrating features of deep layers will obtain relatively precise saliency map.Expand
A novel deep network and aggregation model for saliency detection
TLDR
This paper proposes a novel multi-scale network for saliency detection (MSNSD) consisting of three modules, i.e., bottom-up feature extraction, top-down feature connection and multi- scale saliency prediction, and an input image-aware saliency aggregation method is proposed based on the ridge regression. Expand
Salient object detection via light-weight multi-path cascaded networks
TLDR
A Light-Weight Multi-Path Cascaded Network (LMCN) is proposed for image saliency detection – an encoder-decoder architecture that explicitly exploits all the information available along the down-sampling process to enable full-resolution prediction using long-range residual connections. Expand
Saliency Detection with Deformable Convolution and Feature Attention
TLDR
A novel saliency detection model named DCFA is proposed, which is implemented using a Deformable Feature Extraction Module (DFEM) to focus on the unevenly distributed context features in both low-level details and high-level semantic information. Expand
Global Context-Aware Progressive Aggregation Network for Salient Object Detection
TLDR
This work proposes a novel network named GCPANet to effectively integrate low-level appearance features, high-level semantic features, and global context features through some progressive context-aware Feature Interweaved Aggregation modules and generate the saliency map in a supervised way. Expand
Active Perception Network for Salient Object Detection
TLDR
Active Perception Network (APN) is proposed to enhance inter-feature consistency for salient object detection and aggregate global information, which brings strong semantic consistency to the whole network. Expand
CAGNet: Content-Aware Guidance for Salient Object Detection
TLDR
A Feature Guide Network is proposed which exploits the nature of low-level and high-level features to make foreground and background regions more distinct and suppress the non-salient regions which have “salient-like” appearance and assign foreground label to different-looking salient regions. Expand
Top-Down Fusing Multi-level Contextual Features for Salient Object Detection
TLDR
A novel network architecture is proposed that progressively fuses the rich multi-level contextual features from top to bottom to learn a more effective feature presentation for robust SOD and is superior against state-of-the-arts in terms of all metrics. Expand
Deep Sub-Region Network for Salient Object Detection
TLDR
A novel deep sub-region network equipped with a sequence of sub- Region dilated blocks (SRDB) by aggregating multi-scale salient context information of multiple sub-regions, such that the global context information from the whole image and local contexts from sub-Regions are fused together, making the saliency prediction more accurate. Expand
EDNet: Encoder-Decoder Network with Low Rank and Margin Regularizations for Saliency Detection
  • Jianbo Tang, Dongjing Shan, Weijun Li, Bo Zhao
  • Physics
  • Journal of Physics: Conference Series
  • 2021
Deep learning based methods have achieved great progress in the saliency detection domain. However, it remains to be challenging to segment objects in complicated scenarios consistently andExpand
MASA-Net: Multi-level Aggregated and Self-attentive Network for Fast Salient Object Detection
With the rapid development of convolutional neural network, salient object detection has achieved satisfied visual performance. However, most previous method chooses to focus on either accuracy orExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 51 REFERENCES
Deeply Supervised Salient Object Detection with Short Connections
TLDR
A new saliency method is proposed by introducing short connections to the skip-layer structures within the HED architecture, which produces state-of-the-art results on 5 widely tested salient object detection benchmarks, with advantages in terms of efficiency, effectiveness, and simplicity over the existing algorithms. Expand
Progressive Attention Guided Recurrent Network for Salient Object Detection
TLDR
A novel attention guided network which selectively integrates multi-level contextual information in a progressive manner and introduces multi-path recurrent feedback to enhance this proposed progressive attention driven framework. Expand
Saliency Detection with Recurrent Fully Convolutional Networks
TLDR
This paper develops a new saliency model using recurrent fully convolutional networks (RFCNs) that is able to incorporate saliency prior knowledge for more accurate inference and enables the network to capture generic representations of objects for saliency detection. Expand
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
TLDR
Amulet is presented, a generic aggregating multi-level convolutional feature framework for salient object detection that provides accurate salient object labeling and performs favorably against state-of-the-art approaches in terms of near all compared evaluation metrics. Expand
A Stagewise Refinement Model for Detecting Salient Objects in Images
TLDR
This work proposes to augment feedforward neural networks with a novel pyramid pooling module and a multi-stage refinement mechanism for saliency detection and shows that the proposed method compares favorably against the state-of-the-art approaches. Expand
Deep Contrast Learning for Salient Object Detection
  • Guanbin Li, Yizhou Yu
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This paper proposes an end-to-end deep contrast network that significantly improves the state of the art in salient object detection and extracts segment-wise features very efficiently, and better models saliency discontinuities along object boundaries. Expand
Learning to Detect Salient Objects with Image-Level Supervision
TLDR
This paper develops a weakly supervised learning method for saliency detection using image-level tags only, which outperforms unsupervised ones with a large margin, and achieves comparable or even superior performance than fully supervised counterparts. Expand
Non-local Deep Features for Salient Object Detection
TLDR
A simplified convolutional neural network which combines local and global information through a multi-resolution 4×5 grid structure is proposed which implements a loss function inspired by the Mumford-Shah functional which penalizes errors on the boundary, enabling near real-time, high performance saliency detection. Expand
DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection
  • Nian Liu, Junwei Han
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
Evaluations on four benchmark datasets and comparisons with other 11 state-of-the-art algorithms demonstrate that DHSNet not only shows its significant superiority in terms of performance, but also achieves a real-time speed of 23 FPS on modern GPUs. Expand
Saliency detection by multi-context deep learning
TLDR
This paper proposes a multi-context deep learning framework for salient object detection that employs deep Convolutional Neural Networks to model saliency of objects in images and investigates different pre-training strategies to provide a better initialization for training the deep neural networks. Expand
...
1
2
3
4
5
...