Mingming Gong

Mingming Gong

Auto-generated profile, based on publicly available information

Mingming Gong

Department of Biomedical Informatics, University of Pittsburgh

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 June 2018
Verified
Conference Paper
Closed access
HFHuan Fu
Huan Fu
MGMingming Gong
Mingming Gong
CWChaohui Wang
Chaohui Wang
KBKayhan Batmanghelich
Kayhan Batmanghelich
DTDacheng Tao
Dacheng Tao
Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant improvement by exploring image-level information and hierarchical features from deep convolutional neural networks (DCNNs). These methods model depth estimation as a regression problem and train the regression networks by minimizing mean squared error, which suffers from slow convergence and unsatisfactory local solutions. Besides, existing depth estimation networks employ repeated spatial pooling operations, resulting in undesirable low-resolution feature maps. To obtain high-resolution depth maps, skip-connections or multilayer deconvolution networks are required, which complicates network training and consumes much more computations. To eliminate or at least largely reduce these problems, we introduce a spacing-increasing discretization (SID) strategy to discretize depth and recast depth network learning as an ordinal regression problem. By training the network using an ordinary regression loss, our method achieves much higher accuracy and faster convergence in synch. Furthermore, we adopt a multi-scale network structure which avoids unnecessary spatial pooling and captures multi-scale information in parallel. The proposed deep ordinal regression network (DORN) achieves state-of-the-art results on three challenging benchmarks, i.e., KITTI [16], Make3D [49], and NYU Depth v2 [41], and outperforms existing methods by a large margin.

1 June 2018 in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Verified
Conference Paper
Closed access
XYXiyu Yu
Xiyu Yu
TLTongliang Liu
Tongliang Liu
MGMingming Gong
Mingming Gong
KBKayhan Batmanghelich
Kayhan Batmanghelich
DTDacheng Tao
Dacheng Tao
In this paper, we study the mixture proportion estimation (MPE) problem in a new setting: given samples from the mixture and the component distributions, we identify the proportions of the components in the mixture distribution. To address this problem, we make use of a linear independence assumption, i.e., the component distributions are independent from each other, which is much weaker than assumptions exploited in the previous MPE methods. Based on this assumption, we propose a method (1) that uniquely identifies the mixture proportions, (2) whose output provably converges to the optimal solution, and (3) that is computationally efficient. We show the superiority of the proposed method over the state-of-the-art methods in two applications including learning with label noise and semi-supervised learning on both synthetic and real-world datasets.

1 December 2018
Verified
Journal Article
Closed access
MWMenghan Wang
Menghan Wang
MGMingming Gong
Mingming Gong
XZXiaolin Zheng
Xiaolin Zheng
KZKun Zhang
Kun Zhang

3 April 2019 in arXiv
Verified
Preprint
Open access
PDF file
SZShanshan Zhao
Shanshan Zhao
HFHuan Fu
Huan Fu
MGMingming Gong
Mingming Gong
DTDacheng Tao
Dacheng Tao
Supervised depth estimation has achieved high accuracy due to the advanced deep network architectures. Since the groundtruth depth labels are hard to obtain, recent methods try to learn depth estimation networks in an unsupervised way by exploring unsupervised cues, which are effective but less reliable than true labels. An emerging way to resolve this dilemma is to transfer knowledge from synthetic images with ground truth depth via domain adaptation techniques. However, these approaches overlook specific geometric structure of the natural images in the target domain (i.e., real data), which is important for high-performing depth prediction. Motivated by the observation, we propose a geometry-aware symmetric domain adaptation framework (GASDA) to explore the labels in the synthetic data and epipolar geometry in the real data jointly. Moreover, by training two image style translators and depth estimators symmetrically in an end-to-end network, our model achieves better image style transfer and generates high-quality depth maps. The experimental results demonstrate the effectiveness of our proposed method and comparable performance against the state-of-the-art. Code will be publicly available at: https://github.com/sshan-zhao/GASDA.