Kernel learning for visual perception

Wang, Chen

doi:10.32657/10220/47835

Cited by 5 publications

(4 citation statements)

References 126 publications

(238 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It recently has also been widely applied to correlation filter for improving the processing speed. For example, the kernelized correlation filter (KCF) [22] is proposed to speed up the calculation of kernel ridge regression by bypassing a big matrix inversion, while it assumes that all the data are circular shifts of each other [49], hence it can only predict signal translation. To break this theoretical limitation, the kernel cross-correlator (KCC) is proposed in [54] by defining the correlator in frequency domain directly, resulting in a closed-form solution with computational complexity of O(N log N ), where N is the signal length.…”

Section: Related Workmentioning

confidence: 99%

“…This property is crucial, since when invariances are present in the data, encoding them explicitly in an architecture provides an important source of regularization, which reduces the amount of training data required [23]. As mentioned in Section 2, the same property is also presented in [22], which is achieved by assuming that all the training samples are circular shifts of each other [49], while ours is inherited from convolution. Interestingly, the kernel crosscorrelator (KCC) defined in [54] is equivariant to any affine transforms (e.g., translation, rotation, and scale), which may be useful for further development of this work.…”

Section: Translational Equivariancementioning

confidence: 99%

See 1 more Smart Citation

Kervolutional Neural Networks

Wang

Yang

Xie

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks. However, little effort has been devoted to establishing convolution in non-linear space. Existing works mainly leverage on the activation layers, which can only provide point-wise non-linearity. To solve this problem, a new operation, kervolution (kernel convolution), is introduced to approximate complex behaviors of human perception systems leveraging on the kernel trick. It generalizes convolution, enhances the model capacity, and captures higher order interactions of features, via patch-wise kernel functions, but without introducing additional parameters. Extensive experiments show that kervolutional neural networks (KNN) achieve higher accuracy and faster convergence than baseline CNN.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Translational Equivariancementioning

confidence: 99%

Kervolutional Neural Networks

Wang

Yang

Xie

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

View full text Add to dashboard Cite

show abstract

“…s,t . By the end of an epoch, cross-correlation, also known as discrete convolution-with the difference that convolution operator g is not an impulse function but an arbitrary filter signal [45]-is applied to the τ epoch . This operation can be either in a 1D or 2D spatial frame, based on the specific problem and physical continuity logic among search space locus.…”

Section: Extended Aco For Smart Storage System Managementmentioning

confidence: 99%

Hybrid Forecast and Control Chain for Operation of Flexibility Assets in Micro-Grids

et al. 2021

View full text Add to dashboard Cite

Studies on forecasting and optimal exploitation of renewable resources (especially within microgrids) were already introduced in the past. However, in several research papers, the constraints regarding integration within real applications were relaxed, i.e., this kind of research provides impractical solutions, although they are very complex. In this paper, the computational components (such as photovoltaic and load forecasting, and resource scheduling and optimization) are brought together into a practical implementation, introducing an automated system through a chain of independent services aiming to allow forecasting, optimization, and control. Encountered challenges may provide a valuable indication to make ground with this design, especially in cases for which the trade-off between sophistication and available resources should be rather considered. The research work was conducted to identify the requirements for controlling a set of flexibility assets—namely, electrochemical battery storage system and electric car charging station—for a semicommercial use-case by minimizing the operational energy costs for the microgrid considering static and dynamic parameters of the assets.

show abstract

“…Intuitively, to find the maximum cosine similarity, we need to repeatedly compute (3) for translated memory cube h × w times, resulting in a very high computational complexity. To solve this problem, we leverage the fast Fourier transform (FFT) to compute the cross-correlation [35]. Recall that 2-D cross-correlation is the inner-products between the first signal and circular translations of the second signal [37], we can compute S i (x, M i ) as…”

Section: Memory Readingmentioning

confidence: 99%

Visual Memorability for Robotic Interestingness via Unsupervised Online Learning

Wang,

Qiu

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we aim to solve the problem of interesting scene prediction for mobile robots. This area is currently under explored but is crucial for many practical applications such as autonomous exploration and decision making. First, we expect a robot to detect novel and interesting scenes in unknown environments and lose interests over time after repeatedly observing similar objects. Second, we expect the robots to learn from unbalanced data in a short time, as the robots normally only know the uninteresting scenes before they are deployed. Inspired by those industrial demands, we first propose a novel translationinvariant visual memory for recalling and identifying interesting scenes, then design a three-stage architecture of long-term, short-term, and online learning for human-like experience, environmental knowledge, and online adaption, respectively. It is demonstrated that our approach is able to learn online and find interesting scenes for practical exploration tasks. It also achieves a much higher accuracy than the state-of-the-art algorithm on very challenging robotic interestingness prediction datasets.

show abstract

Kernel learning for visual perception

Abstract: The contributions of the co-authors are as follows: • I proposed the idea, designed the experiments, and prepared the manuscript. • Handuo Zhang, Thien-Minh Nguyen, and I conducted the experiments.

Cited by 5 publications

References 126 publications

Kervolutional Neural Networks

Kervolutional Neural Networks

Hybrid Forecast and Control Chain for Operation of Flexibility Assets in Micro-Grids

Visual Memorability for Robotic Interestingness via Unsupervised Online Learning

Contact Info

Product

Resources

About