Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread

@article{Li2020DepthwiseNM,
  title={Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread},
  author={Hao-Feng Li and Guanbin Li and Binbin Yang and Guanqi Chen and Liang Lin and Yizhou Yu},
  journal={IEEE transactions on cybernetics},
  year={2020}
}
Recently, deep convolutional neural networks have achieved significant success in salient object detection. However, existing state-of-the-art methods require high-end GPUs to achieve real-time performance, which makes it hard to adapt to low cost or portable devices. Although generic network architectures have been proposed to speed up inference on mobile devices, they are tailored to the task of image classification or semantic segmentation, and struggle to capture intrachannel and… Expand
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. Expand
DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection
TLDR
The proposed saliency detector, a modified U-Net architecture with DNA, performs favorably against state-of-the-art methods on various datasets and evaluation metrics without bells and whistles and can successfully break through the bottleneck of the current linear approaches. Expand
Rethinking Image Salient Object Detection: Object-Level Semantic Saliency Reranking First, Pixelwise Saliency Refinement Later
TLDR
This paper divides the SOD problem into two sequential steps, and is the first attempt to consider salient object detection as mainly an object-level semantic reranking problem, and aims at investigating the object- level semantic ranks between multiple images. Expand
Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter
TLDR
This paper is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem, and proposes a lightweight, weakly supervised deep network to coarsely locate those semantically salient regions first and selectively fuse multiple off-the-shelf deep models on these semantically relevant regions as the pixel-wise saliency refinement. Expand
Salient Objects in Clutter
TLDR
It is argued that improving the dataset can yield higher performance gains than focusing only on the decoder design, and several dataset-enhancement strategies are investigated, including label smoothing to implicitly emphasize salient boundaries, random image augmentation to adapt saliency models to various scenarios, and self-supervised learning as a regularization strategy to learn from small datasets. Expand
Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net
  • Yu Qiu, Yun Liu, Le Zhang, Jing Xu
  • Computer Science
  • ArXiv
  • 2021
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. Expand
Robust Real-World Image Super-Resolution against Adversarial Attacks
  • Jiutao Yue, Haofeng Li, Pengxu Wei, Guanbin Li, Liang Lin
  • Computer Science
  • ACM Multimedia
  • 2021
TLDR
A robust deep learning framework for real-world SR that randomly erases potential adversarial noises in the frequency domain of input images or features and is more insensitive to adversarial attacks and presents more stable SR results than existing models and defenses is proposed. Expand

References

SHOWING 1-10 OF 64 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
Contrast-Oriented Deep Neural Networks for Salient Object Detection
  • Guanbin Li, Yizhou Yu
  • Computer Science, Medicine
  • IEEE Transactions on Neural Networks and Learning Systems
  • 2018
TLDR
This paper develops hybrid contrast-oriented deep neural networks that can significantly outperform the state of the art in terms of all popular evaluation metrics. Expand
Salient Object Detection with Recurrent Fully Convolutional Networks
TLDR
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. 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
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. 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
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
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
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
TLDR
Flow guided recurrent neural encoder (FGRNE) is presented, an accurate and end-to-end learning framework for video salient object detection that significantly outperforms state-of-the-art methods on the public benchmarks of DAVIS and FBMS. Expand
...
1
2
3
4
5
...