DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection

@article{Liu2021DNADN,
  title={DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection},
  author={Yun Liu and Deng-Ping Fan and Guangyu Nie and Xinyu Zhang and Vahan Petrosyan and Ming-Ming Cheng},
  journal={IEEE transactions on cybernetics},
  year={2021},
  volume={PP}
}
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multiscale convolutional features in convolutional neural networks (CNNs). Many popular methods impose deep supervision to perform side-output predictions that are linearly aggregated for final saliency prediction. In this article, we theoretically and experimentally demonstrate that linear aggregation of side-output predictions is suboptimal, and it only makes limited use of the side-output… 
Residual feature pyramid networks for salient object detection
TLDR
This work proposes novel residual feature pyramid networks with richer convolutional features to fully exploit multi-scale and multi-level information of objects and outperforms 17 recent state-of-the-art methods for accurate SOD.
Lightweight Salient Object Detection via Hierarchical Visual Perception Learning
TLDR
A hierarchical visual perception (HVP) module to imitate the primate visual cortex for hierarchical perception learning is proposed, and with the HVP module incorporated, a lightweight SOD network is designed, namely, HVPNet.
Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net
TLDR
ABiU-Net provides a new perspective for transformer-based SOD and performs favorably against previous state-of-the-art SOD methods, and takes advantage of the natural properties of transformer and CNN.
A simple saliency detection approach via automatic top-down feature fusion
TLDR
An Automatic Top-Down Fusion (ATDF) method, in which the global information at the top sides are flowed into bottom sides to guide the learning of low layers, is proposed, which opens a new path for saliency detection.
SAMNet: Stereoscopically Attentive Multi-Scale Network for Lightweight Salient Object Detection
TLDR
This work introduces a novel Stereoscopically Attentive Multi-scale (SAM) module, which adopts a stereoscopic attention mechanism to adaptively fuse the features of various scales to promote more practical SOD systems.
EDN: Salient Object Detection via Extremely-Downsampled Network
TLDR
An Extremely-Downsampled Network (EDN) is introduced, which employs an extreme downsampling technique to effectively learn a global view of the whole image, leading to accurate salient object localization.
Hierarchical and Interactive Refinement Network for Edge-Preserving Salient Object Detection
TLDR
A novel multi-stage and dual-path network structure is designed to estimate the salient edges and regions from the low-level and high-level feature maps, respectively, to preserve the edge structures in detecting salient objects.
Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation.
TLDR
This paper proposes a multiple instance learning (MIL) framework, which can be trained in an end-to-end manner using training images with image-level labels and achieves state-of-the-art performance for both weakly supervised instance segmentation and semantic segmentation.
Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
TLDR
This paper presents a novel loss function, called class-agnostic segmentation (CAS) loss, which doesn’t require to define the label of a class a-priori, rather the CAS loss clusters regions with similar appearance together in a weakly-supervised manner.
Region Refinement Network for Salient Object Detection
TLDR
A Region Refinement Network (RRN), which recurrently filters redundant information and explicitly models boundary information for saliency detection and a Boundary Refinement Loss (BRL) that adds extra supervision for better distinguishing foreground from background.
...
1
2
3
...

References

SHOWING 1-10 OF 118 REFERENCES
Richer and Deeper Supervision Network for Salient Object Detection
TLDR
This work proposes a new SOD system which aims at designing a more efficient and effective way to pass back global information and shows the proposed RDS network achieves the state-of-the-art results on five public SOD datasets.
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.
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
TLDR
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.
Reverse Attention for Salient Object Detection
TLDR
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.
Attentive Feedback Network for Boundary-Aware Salient Object Detection
TLDR
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.
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.
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.
BASNet: Boundary-Aware Salient Object Detection
TLDR
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.
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.
Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector
  • Dingwen Zhang, Junwei Han, Yu Zhang
  • Computer Science
    2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
TLDR
This paper makes the earliest effort to train a deep salient object detector without using any human annotation and can approach the same network trained with full supervision and even outperform a number of fully supervised state-of-the-art approaches.
...
1
2
3
4
5
...