Salient Object Detection With Purificatory Mechanism and Structural Similarity Loss

  title={Salient Object Detection With Purificatory Mechanism and Structural Similarity Loss},
  author={Jia Li and Jinming Su and Changqun Xia and Yonghong Tian},
  journal={IEEE Transactions on Image Processing},
Image-based salient object detection has made great progress over the past decades, especially after the revival of deep neural networks. By the aid of attention mechanisms to weight the image features adaptively, recent advanced deep learning-based models encourage the predicted results to approximate the ground-truth masks with as large predictable areas as possible, thus achieving the state-of-the-art performance. However, these methods do not pay enough attention to small areas prone to… 
3 Citations
Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection
This paper designs a democratic prototype generation module to generate democratic response maps, covering sufficient co-salient regions and thereby involving more shared attributes of co- salient objects, and proposes a self-contrastive learning module, where both positive and negative pairs are formed without relying on additional classification information.
RGB-D Salient Object Detection With Ubiquitous Target Awareness
This work makes the first attempt to solve the RGB-D salient object detection problem with a novel depth-awareness framework and proposes a Ubiquitous Target Awareness (UTA) network, which not only surpasses the state-of-the-art methods on five publicRGB-D SOD benchmarks by a large margin, but also verifies its extensibility.


Attentive Feedback Network for Boundary-Aware Salient Object Detection
The Attentive Feedback Modules (AFMs) are designed to better explore the structure of objects and produce satisfying results on the object boundaries and achieves state-of-the-art performance on five widely tested salient object detection benchmarks.
BASNet: Boundary-Aware Salient Object Detection
Experimental results on six public datasets show that the proposed predict-refine architecture, BASNet, outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures.
Reverse Attention for Salient Object Detection
An accurate yet compact deep network for efficient salient object detection that employs residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy.
Deeply Supervised Salient Object Detection with Short Connections
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.
Multi-Scale Interactive Network for Salient Object Detection
The consistency-enhanced loss is exploited to highlight the fore-/back-ground difference and preserve the intra-class consistency in the aggregate interaction modules to integrate the features from adjacent levels, in which less noise is introduced because of only using small up-/down-sampling rates.
Salient Object Detection with Recurrent Fully Convolutional Networks
A new saliency detection method based on recurrent fully convolutional networks (RFCNs) that is able to incorpor- ate saliency prior knowledge for more accurate inference and to automatically learn to refine the saliency map by iteratively correcting its previous errors, yielding more reliable final predictions.
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
A novel Cascaded Partial Decoder (CPD) framework for fast and accurate salient object detection and applies the proposed framework to optimize existing multi-level feature aggregation models and significantly improve their efficiency and accuracy.
A Stagewise Refinement Model for Detecting Salient Objects in Images
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.
Learning to Detect Salient Objects with Image-Level Supervision
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.
A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision
This work proposes to train saliency detection networks by exploiting the supervision from not only salient object detection, but also foreground contour detection and edge detection, and develops a novel mutual learning module (MLM), which improves the performance by a large margin.