FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method

Rouhsedaghat, Mozhdeh; Wang, Yifan; Ge, Xiou; Hu, Shuowen; You, Suya; Kuo, C.-C. Jay

doi:10.1007/978-3-030-68793-9_12

Cited by 25 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To implement SSL, PixelHop [35] and PixelHop++ [27] offers powerful hierarchical representations and plays a key role of dimension reduction in TGHop. SSL-based solutions have been proposed to tackle quite a few problems, including [36][37][38][39][40][41][42][43][44][45]. In this work, we present an SSL-based texture image generation method.…”

Section: C) Successive Subspace Learningmentioning

confidence: 99%

TGHop: an explainable, efficient, and lightweight method for texture generation

Lei

Zhao

Zhang

et al. 2021

SIP

View full text Add to dashboard Cite

An explainable, efficient, and lightweight method for texture generation, called TGHop (an acronym of Texture Generation PixelHop), is proposed in this work. Although synthesis of visually pleasant texture can be achieved by deep neural networks, the associated models are large in size, difficult to explain in theory, and computationally expensive in training. In contrast, TGHop is small in its model size, mathematically transparent, efficient in training and inference, and able to generate high-quality texture. Given an exemplary texture, TGHop first crops many sample patches out of it to form a collection of sample patches called the source. Then, it analyzes pixel statistics of samples from the source and obtains a sequence of fine-to-coarse subspaces for these patches by using the PixelHop++ framework. To generate texture patches with TGHop, we begin with the coarsest subspace, which is called the core, and attempt to generate samples in each subspace by following the distribution of real samples. Finally, texture patches are stitched to form texture images of a large size. It is demonstrated by experimental results that TGHop can generate texture images of superior quality with a small model size and at a fast speed.

show abstract

Section: C) Successive Subspace Learningmentioning

confidence: 99%

TGHop: an explainable, efficient, and lightweight method for texture generation

Lei

Zhao

Zhang

et al. 2021

SIP

View full text Add to dashboard Cite

show abstract

“…Multi-stage Saab transform filters are learned in a one-pass feedforward manner. Green learning has been applied to image classification (e.g., PixelHop [26] and PixelHop++ [27]) and point cloud processing (e.g., PointHop [28], PointHop++ [29], SPA [30], UFF [31], R-PointHop [2], GSIP [32]), face biomerics (e.g., DefakeHop [33], FaceHop [34]), anomaly localization [35] and texture generation [36].…”

Section: Green Learning and Pointhop++mentioning

confidence: 99%

GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method

Kadam¹,

Zhang²,

Gu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Visual odometry aims to track the incremental motion of an object using the information captured by visual sensors. In this work, we study the point cloud odometry problem, where only the point cloud scans obtained by the LiDAR (Light Detection And Ranging) are used to estimate object's motion trajectory. A lightweight point cloud odometry solution is proposed and named the green point cloud odometry (GPCO) method. GPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans. It consists of three steps. First, a geometry-aware point sampling scheme is used to select discriminant points from the large point cloud. Second, the view is partitioned into four regions surrounding the object, and the PointHop++ method is used to extract point features. Third, point correspondences are established to estimate object motion between two consecutive scans. Experiments on the KITTI dataset are conducted to demonstrate the effectiveness of the GPCO method. It is observed that GPCO outperforms benchmarking deep learning methods in accuracy while it has a significantly smaller model size and less training time.

show abstract

“…It is the first of convolutional neural network method, which is used for handwritten numeral recognition. LeNet also known as leNet-5 [7] , has one input layer, two convolution layers, two pool layers, two full connection layers and one output layer (the last full connection layer is the output layer). The first input layer, C1 and S2 are the first convolution layer and the first pool layer respectively; C3 and S4 are the second convolution layer and the second pool layer respectively; C5 is the third convolution layer; F6 is the full link layer; The last layer is the output layer.…”

Section: Lenetmentioning

confidence: 99%

Image recognition algorithms based on deep learning

Xie

Chen

et al. 2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Convolutional neural network is a very important research direction in deep learning technology. According to the current development of convolutional network, in this paper, convolutional neural networks are induced. Firstly, this paper induces the development process of convolutional neural network; then it introduces the structure of convolutional neural network and some typical convolutional neural networks. Finally, several examples of the application of deep learning is introduced.

show abstract

FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method

Cited by 25 publications

References 29 publications

TGHop: an explainable, efficient, and lightweight method for texture generation

TGHop: an explainable, efficient, and lightweight method for texture generation

GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Method

Image recognition algorithms based on deep learning

Contact Info

Product

Resources

About