Machine Learning (2020 BAAI Conference)There are some classic papers on the topic of ‘Machine Learning’.
IEEE Transactions on Information Theory, no. 3 (2020): 1785-1821
We study the convolutional phase retrieval problem, of recovering an unknown signal <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$x \in \mathbb C^{n}$ </tex-math></inline-formula> from <i...
0
0
IEEE transactions on neural networks and learning systems, pp.1-15, (2020)
We propose a structured robust adaptive dictionary pair learning framework for the discriminative sparse representation learning
0
0
Jiahuan Ren,
IEEE Trans. Image Processing, (2020): 3941-3956
In this paper, we investigate the robust dictionary learning (DL) to discover the hybrid salient low-rank and sparse representation in a factorized compressed space. A Joint Robust Factorization and Projective Dictionary Learning (J-RFDL) model is presented. The setting of J-RFDL...
0
0
arxiv, (2020)
We point out that elaborately shrunk search space can improve the performance of existing Neural Architecture Search algorithms
0
0
Cai Yuanhao, Luo Zhengxiong, Yin Binyi, Du Angang, Wang Haoqian,
We propose a novel network Residual Steps Network for human pose estimation
0
0
International Conference on Computer Vision, (2019): 3435-3444
We address the problem of reducing spatial redundancy that widely exists in vanilla Convolutional Neural Networks models, and propose a novel Octave Convolution operation to store and process low- and high-frequency features separately to improve the model efficiency
0
0
CVPR, (2019): 433-442
We present a highly efficient approach for global reasoning that can be effectively implemented by projecting information from the coordinate space to nodes in an interaction space graph where we can directly reason over globally-aware discriminative features
0
0
arXiv: Computer Vision and Pattern Recognition, (2019)
The computation cost is unaffordable on large datasets
0
0
IEEE Transactions on Pattern Analysis and Machine Intelligence, no. 6 (2019): 1377-1393
To restore images captured in the environment with both rain accumulation and heavy rain, we introduced an recurrent rain detection and removal network that progressively removes rain streaks, embedded with the rain-accumulation removal network
0
0
Zeming Li, Yiping Bao,
ICCV, pp.6717-6726, (2019)
We investigate the balance between the input resolution, the backbone, and the detection head
0
0
Wenbo Li, Binyi Yin, Qixiang Peng, Tianzi Xiao,
arXiv: Computer Vision and Pattern Recognition, (2019)
We propose a Multi-Stage Pose Network to perform multi-person pose estimation
0
0
IEEE Transactions on Knowledge and Data Engineering, pp.1-1, (2019)
We proposed a new and robust semi-supervised adaptive concept factorization algorithm that aim at improving the discriminating ability of the new representations and the robustness properties to noise and gross sparse errors
0
0
International Conference on Computer Vision, (2019): 3296-3305
We have presented MetaPruning for channel pruning with following advantages: 1) it achieves much higher accuracy than the uniform pruning baselines as well as other state-of-the-art channel pruning methods, both traditional and AutoML-based; 2) it can flexibly optimize with respe...
0
0
Jiahuan Ren,
IEEE Transactions on Circuits and Systems for Video Technology, (2019): 1-1
We propose a joint subspace recovery and enhanced locality based robust flexible label consistent dictionary learning method called Robust Flexible Discriminative Dictionary Learning (RFDDL). RFDDL mainly improves the data representation and classification abilities by enhancin...
0
0
IEEE Transactions on Big Data, (2019): 1-1
We have proposed a novel kernel-induced label propagation framework termed Kernel-Label Propagation by mapping for semi-supervised classification
0
0
IEEE Transactions on Knowledge and Data Engineering, pp.1-1, (2019)
Concept Factorization (CF) and its variants may produce inaccurate representation and clustering results due to the sensitivity to noise, hard constraint on the reconstruction error and pre-obtained approximate similarities. To improve the representation ability, a novel unsupe...
Cited by4BibtexViews33
0
0
IEEE transactions on cybernetics, pp.1-12, (2019)
We propose a joint kernel regression model to learn the regression variable, which is called feature translator in this article
0
0
Mengxiao Lin,
computer vision and pattern recognition, (2018)
Even though depthwise convolution usually has very low theoretical complexity, we find it difficult to efficiently implement on lowpower mobile devices, which may result from a worse computation/memory access ratio compared with other dense operations
0
1
Zhenli Zhang, Dazhi Cheng,
ECCV, (2018): 273-288
Better feature fusion is demonstrated by the performance boost when fusing with original low-level features and the overall segmentation performance is improved by a large margin
0
0
IEEE Transactions on Medical Imaging, no. 2 (2018): 371-382
As mentioned in Section IV-A, the model structure should be determined before the 3pADMM is optimized for low-dose CT reconstruction, and we conducted extensive experiments to evaluate the significance of different model structures
0
0
Keywords
Image ResolutionDictionariesImage ReconstructionLight FieldOptimizationPattern RecognitionSignal Processing AlgorithmsAlgorithm Design And AnalysisComputer VisionConvergence
Authors
Paper 11
Paper 11
Paper 10
Paper 10
Paper 9
Paper 9
Paper 6
Paper 6
Paper 6
Paper 6