Mengyang Feng

Mengyang Feng

Auto-generated profile, based on publicly available information

Mengyang Feng

School of Information and Communication Engineering, Dalian University of Technology, Dalian, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2017
Verified
Conference Paper
Closed access
LWLijun Wang
Lijun Wang
HLHuchuan Lu
Huchuan Lu
YWYifan Wang
Yifan Wang
MFMengyang Feng
Mengyang Feng
DWDong Wang
Dong Wang
XRXiang Ruan
Xiang Ruan
Deep Neural Networks (DNNs) have substantially improved the state-of-the-art in salient object detection. However, training DNNs requires costly pixel-level annotations. In this paper, we leverage the observation that image-level tags provide important cues of foreground salient objects, and develop a weakly supervised learning method for saliency detection using image-level tags only. The Foreground Inference Network (FIN) is introduced for this challenging task. In the first stage of our training method, FIN is jointly trained with a fully convolutional network (FCN) for image-level tag prediction. A global smooth pooling layer is proposed, enabling FCN to assign object category tags to corresponding object regions, while FIN is capable of capturing all potential foreground regions with the predicted saliency maps. In the second stage, FIN is fine-tuned with its predicted saliency maps as ground truth. For refinement of ground truth, an iterative Conditional Random Field is developed to enforce spatial label consistency and further boost performance. Our method alleviates annotation efforts and allows the usage of existing large scale training sets with image-level tags. Our model runs at 60 FPS, outperforms unsupervised ones with a large margin, and achieves comparable or even superior performance than fully supervised counterparts.

1 June 2019
Verified
Conference Paper
Closed access
MFMengyang Feng
Mengyang Feng
HLHuchuan Lu
Huchuan Lu
EDErrui Ding
Errui Ding
Recent deep learning based salient object detection methods achieve gratifying performance built upon Fully Convolutional Neural Networks (FCNs). However, most of them have suffered from the boundary challenge. The state-of-the-art methods employ feature aggregation tech- nique and can precisely find out wherein the salient object, but they often fail to segment out the entire object with fine boundaries, especially those raised narrow stripes. So there is still a large room for improvement over the FCN based models. In this paper, we design the Attentive Feedback Modules (AFMs) to better explore the structure of objects. A Boundary-Enhanced Loss (BEL) is further employed for learning exquisite boundaries. Our proposed deep model produces satisfying results on the object boundaries and achieves state-of-the-art performance on five widely tested salient object detection benchmarks. The network is in a fully convolutional fashion running at a speed of 26 FPS and does not need any post-processing.

5 October 2018
Verified
Book Chapter
Closed access
PDF file
YZYunhua Zhang
Yunhua Zhang
LWLijun Wang
Lijun Wang
JQJinqing Qi
Jinqing Qi
Dong WangDong Wang
Dong Wang
MFMengyang Feng
Mengyang Feng
HLHuchuan Lu
Huchuan Lu

1 June 2019
Verified
Conference Paper
Closed access
RWRunmin Wu
Runmin Wu
MFMengyang Feng
Mengyang Feng
WGWenlong Guan
Wenlong Guan
DWDong Wang
Dong Wang
HLHuchuan Lu
Huchuan Lu
EDErrui Ding
Errui Ding
Though deep learning techniques have made great progress in salient object detection recently, the predicted saliency maps still suffer from incomplete predictions due to the internal complexity of objects and inaccurate boundaries caused by strides in convolution and pooling operations. To alleviate these issues, we propose to train saliency detection networks by exploiting the supervision from not only salient object detection, but also foreground contour detection and edge detection. First, we leverage salient object detection and foreground contour detection tasks in an intertwined manner to generate saliency maps with uniform highlight. Second, the foreground contour and edge detection tasks guide each other simultaneously, thereby leading to preciser foreground contour prediction and reducing the local noises for edge prediction. In addition, we develop a novel mutual learning module (MLM) which serves as the building block of our method. Each MLM consists of multiple network branches trained in a mutual learning manner, which improves the performance by a large margin. Extensive experiments on seven challenging datasets demonstrate that the proposed method has delivered state-of-the-art results in both salient object detection and edge detection.

28 February 2020 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
MFMengyang Feng
Mengyang Feng
HLHuchuan Lu
Huchuan Lu
YYYizhou Yu
Yizhou Yu
Recent deep learning based salient object detection methods improve the performance by introducing multi-scale strategies into fully convolutional neural networks (FCNs). The final result is obtained by integrating all the predictions at each scale. However, the existing multi-scale based methods suffer from several problems: 1) it is difficult to directly learn discriminative features and filters to regress high-resolution saliency masks for each scale; 2) rescaling the multi-scale features could pull in many redundant and inaccurate values, and this weakens the representational ability of the network. In this paper, we propose a residual learning strategy and introduce to gradually refine the coarse prediction scale-by-scale. Concretely, instead of directly predicting the finest-resolution result at each scale, we learn to predict residuals to remedy the errors between coarse saliency map and scale-matching ground truth masks. We employ a Dilated Convolutional Pyramid Pooling (DCPP) module to generate the coarse prediction and guide the the residual learning process through several novel Attentional Residual Modules (ARMs). We name our network as Residual Refinement Network (R 2 Net). We demonstrate the effectiveness of the proposed method against other state-of-the-art algorithms on five released benchmark datasets. Our R 2 Net is a fully convolutional network which does not need any post-processing and achieves a real-time speed of 33 FPS when it is run on one GPU.

23 February 2018 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YQYao Qin
Yao Qin
MFMengyang Feng
Mengyang Feng
HLHuchuan Lu
Huchuan Lu
GCGarrison W. Cottrell
Garrison W. Cottrell