CVPR2018的显著性文章一览

没有找到太完整的合集，只好自己动手从CVPR18的文章列表中扒了。搜索关键词： Saliency 和 Salience ，以及 Salient

Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos

Hsien-Tzu Cheng, Chun-Hung Chao, Jin-Dong Dong, Hao-Kai Wen, Tyng-Luh Liu, Min Sun

并不是普通的显著性检测。贴摘要：

Automatic saliency prediction in 360◦ videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). We propose a spatial-temporal network which is (1) weakly-supervised trained and (2) tailor-made for 360◦ viewing sphere. Note that most existing methods are less scalable since they rely on annotated saliency map for training. Most importantly, they convert 360◦ sphere to 2D images (e.g., a single equirectangular（等距离长方圆柱） image or multiple separate Normal Field-of-View （正常视野）(NFoV) images) which introduces distortion and image boundaries. In contrast, we propose a simple and effective Cube Padding (CP) technique as follows.

1. Firstly, we render the 360◦ view on six faces of a cube using perspective projection. Thus, it introduces very little distortion（失真）.
2. Then, we concatenate all six faces while utilizing the connectivity between faces on the cube for image padding (i.e., Cube Padding) in convolution, pooling, convolutional LSTM layers.
3. In this way, CP introduces no image boundary while being applicable to almost all Convolutional Neural Network (CNN) structures.

To evaluate our method, we propose Wild-360, a new 360◦ video saliency dataset, containing challenging videos with saliency heatmap annotations. In experiments, our method outperforms baseline methods in both speed and quality.

可以看到有几个点：

• weakly-supervised trained
• 专为360°视场量身定做
• 提出了一个新的360°视频显著性数据集

相关链接

• 论文：http://openaccess.thecvf.com/content_cvpr_2018/papers/Cheng_Cube_Padding_for_CVPR_2018_paper.pdf
• 代码：https://github.com/hsientzucheng/CP-360-Weakly-Supervised-Saliency
• 项目：http://aliensunmin.github.io/project/360saliency/

Learning to Promote Saliency Detectors

Yu Zeng, Huchuan Lu, Lihe Zhang, Mengyang Feng, Ali Borji

• 使用了zero-shot learning的思想构建了一个训练好的用于“后处理”的分支来进一步优化现有网络的预测
• 引入超分辨重建的方法——亚像素卷积的方法来回复分辨率（实际使用的是转置卷积）
• 迭代训练与测试，寻找最优的次数（不喜欢这种设计，R3Net也是这样，感觉不实际，迭代这种操作反而就是在不断暴力寻找最合适的模型，这个真的能反映出来模块设计的有效性么）

语雀内容

PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection

Nian Liu, Junwei Han, Ming-Hsuan Yang

• 全局（双向LSTM的组合）与局部注意力（普通卷积处理，这里考虑了两种容和注意力的方法，矩阵乘法和哈达马乘积）的构造，另外构造了一个注意力卷积实现对于特征的门控处理
• 为了促进训练, 对每个解码模块采用了深监督的策略. 然后将真值放缩到对应解码器模块输出预测的大小进行监督，同时提出一种全局注意力损失，只针对最后一层的输出进行计算。

相关链接

• 论文（新旧两稿结构不同）：
  • 旧稿：https://arxiv.org/abs/1708.06433
  • 新稿：https://arxiv.org/pdf/1812.06314.pdf
• 代码（PyTorch重现）：https://github.com/Ugness/PiCANet-Implementation
• 之前的记录：https://github.com/lartpang/Machine-Deep-Learning/blob/master/%E5%9B%BE%E5%83%8F%E5%88%86%E5%89%B2/PiCANet:%20Pixel-wise%20Contextual%20AttentionLearning%20for%20Accurate%20Saliency%20Detection%E6%80%BB%E7%BB%93(2018).md.md)
  

Detect Globally, Refine Locally: A Novel Approach to Saliency Detection

Tiantian Wang, Lihe Zhang, Shuo Wang, Huchuan Lu, Gang Yang, Xiang Ruan, Ali Borji

语雀内容

Revisiting Video Saliency: A Large-Scale Benchmark and a New Model

Wenguan Wang, Jianbing Shen, Fang Guo, Ming-Ming Cheng, Ali Borji

Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional Push

Siavash Gorji, James J. Clark

We presented a framework which benefits from the recent development in static saliency models in predicting the fixation patterns on videos.

针对视频的眼动预测。

Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation

Qihang Yu, Lingxi Xie, Yan Wang, Yuyin Zhou, Elliot K. Fishman, Alan L. Yuille

这篇是做医学图像分割的。

Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective

Jing Zhang, Tong Zhang, Yuchao Dai, Mehrtash Harandi, Richard Hartley

Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display

Shizheng Wang, Wenjuan Liao, Phil Surman, Zhigang Tu, Yuanjin Zheng, Junsong Yuan

Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional Push

Siavash Gorji, James J. Clark

Progressive Attention Guided Recurrent Network for Salient Object Detection

Xiaoning Zhang, Tiantian Wang, Jinqing Qi, Huchuan Lu, Gang Wang

Salient Object Detection Driven by Fixation Prediction

Wenguan Wang, Jianbing Shen, Xingping Dong, Ali Borji

A Bi-Directional Message Passing Model for Salient Object Detection

Lu Zhang, Ju Dai, Huchuan Lu, You He, Gang Wang

• 多尺度特征融合
• 双向信息传递机制
• 门控机制，控制信息传递

语雀内容

Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection

Hao Chen, Youfu Li

Flow Guided Recurrent Neural Encoder for Video Salient Object Detection

Guanbin Li, Yuan Xie, Tianhao Wei, Keze Wang, Liang Lin

Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects

Md Amirul Islam, Mahmoud Kalash, Neil D. B. Bruce

相关链接

• CVPR 2018 Saliency Detection 论文：https://blog.csdn.net/jizhidexiaoming/article/details/80959891