Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

@article{Zhang2017AmuletAM,
  title={Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection},
  author={Pingping Zhang and D. Wang and Huchuan Lu and Hongyu Wang and Xiang Ruan},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={202-211}
}
Fully convolutional neural networks (FCNs) have shown outstanding performance in many dense labeling problems. [] Key Method Our framework first integrates multi-level feature maps into multiple resolutions, which simultaneously incorporate coarse semantics and fine details. Then it adaptively learns to combine these feature maps at each resolution and predict saliency maps with the combined features. Finally, the predicted results are efficiently fused to generate the final saliency map.

Figures and Tables from this paper

Hierarchical Salient Object Detection Network with Dense Connections
TLDR
This work proposes a novel pixel-wise salient object detection network based on FCN by aggregating multi-level feature maps and introduces skip-layer structure for providing a better feature representation and helping shallow side outputs locate salient objects.
Salient Object Detection via Recurrently Aggregating Spatial Attention Weighted Cross-Level Deep Features
TLDR
This paper proposes a novel deep saliency detection network by recurrently aggregating and refining features in a cross-level and spatial attention-aware manner that outperforms other 14 state-of-the-art competitors.
Salient Object Detection Using Recurrent Guidance Network With Hierarchical Attention Features
TLDR
A recurrent guidance network is proposed to correct the biased salient regions, which can effectively suppress the distractions in background and progressively refine salient objects boundaries.
Boundary-Guided Feature Aggregation Network for Salient Object Detection
TLDR
A novel FCN framework to integrate multilevel convolutional features recurrently with the guidance of object boundary information and fuse boundary information into salient regions to achieve accurate boundary inference and semantic enhancement is proposed.
Global contextual guided residual attention network for salient object detection
TLDR
A residual attention learning strategy and a multistage refinement mechanism to gradually refine the coarse prediction in a scale-by-scale manner and adopt multiscale cross-entropy loss to guide network learning salient features are proposed.
Recurrently Aggregating Deep Features for Salient Object Detection
TLDR
This paper develops a novel deep saliency network equipped with recurrently aggregated deep features (RADF) to more accurately detect salient objects from an image by fully exploiting the complementary saliency information captured in different layers.
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.
DSFMA: deeply supervised fully convolutional neural networks based on multi-level aggregation for saliency detection
TLDR
This paper presents a novel multi-level aggregation method by following a U-shaped architecture of the VGG-16 network and integrates the recurrent convolutional layers (RCLs) into the model, which provide more deepness and enhance the capability to integrate more contextual knowledge.
...
...

References

SHOWING 1-10 OF 53 REFERENCES
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
TLDR
This paper proposes a multi-task deep saliency model based on a fully convolutional neural network with global input (whole raw images) and global output (Whole saliency maps) and presents a graph Laplacian regularized nonlinear regression model for saliency refinement.
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.
Deep Contrast Learning for Salient Object Detection
  • Guanbin Li, Yizhou Yu
  • Computer Science, Environmental 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.
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.
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.
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.
Salient Object Detection: A Discriminative Regional Feature Integration Approach
TLDR
This paper presents a principled extension, supervised feature integration, which learns a random forest regressor to discriminatively integrate the saliency features for saliency computation and significantly outperforms state-of-the-art methods on seven benchmark datasets.
Deep Saliency with Encoded Low Level Distance Map and High Level Features
TLDR
It is demonstrated that hand-crafted features can provide complementary information to enhance performance of saliency detection that utilizes only high level features.
Visual saliency based on multiscale deep features
  • Guanbin Li, Yizhou Yu
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
This paper discovers that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks.
Holistically-Nested Edge Detection
  • Saining Xie, Z. Tu
  • Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
TLDR
HED performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets, and automatically learns rich hierarchical representations that are important in order to resolve the challenging ambiguity in edge and object boundary detection.
...
...