Search Results for author:
Found 18 papers, 3 papers with code
LSR: A Light-Weight Super-Resolution Method
A light-weight super-resolution (LSR) method from a single image targeting mobile applications is proposed in this work.
Point Cloud Attribute Compression via Successive Subspace Graph Transform
Inspired by the recently proposed successive subspace learning (SSL) principles, we develop a successive subspace graph transform (SSGT) to address point cloud attribute compression in this work.
PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification
In PixelHop++, one can control the learning model size of fine-granularity, offering a flexible tradeoff between the model size and the classification performance.
PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification
A new machine learning methodology, called successive subspace learning (SSL), is introduced in this work.
Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks
A semi-supervised learning framework using the feedforward-designed convolutional neural networks (FF-CNNs) is proposed for image classification in this work.
Ensembles of feedforward-designed convolutional neural networks
An ensemble method that fuses the output decision vectors of multiple feedforward-designed convolutional neural networks (FF-CNNs) to solve the image classification problem is proposed in this work.
Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation
Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects.
Towards Visible and Thermal Drone Monitoring with Convolutional Neural Networks
One is a model-based drone augmentation technique that automatically generates visible drone images with a bounding box label on the drone's location.
Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation
Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets.
Analysis on Gradient Propagation in Batch Normalized Residual Networks
We conduct mathematical analysis on the effect of batch normalization (BN) on gradient backpropogation in residual network training, which is believed to play a critical role in addressing the gradient vanishing/explosion problem, in this work.
An Interpretable Generative Model for Handwritten Digit Image Synthesis
An interpretable generative model for handwritten digits synthesis is proposed in this work.
Interpretable Convolutional Neural Networks via Feedforward Design
To construct convolutional layers, we develop a new signal transform, called the Saab (Subspace Approximation with Adjusted Bias) transform.
Defense Against Adversarial Attacks with Saak Transform
Therefore, we propose a Saak transform based preprocessing method with three steps: 1) transforming an input image to a joint spatial-spectral representation via the forward Saak transform, 2) apply filtering to its high-frequency components, and, 3) reconstructing the image via the inverse Saak transform.
A Deep Learning Approach to Drone Monitoring
A drone monitoring system that integrates deep-learning-based detection and tracking modules is proposed in this work.
A Saak Transform Approach to Efficient, Scalable and Robust Handwritten Digits Recognition
We conduct a comparative study on the performance of the LeNet-5 and the Saak-transform-based solutions in terms of scalability and robustness as well as the efficiency of lossless and lossy Saak transforms under a comparable accuracy level.
On Data-Driven Saak Transform
The Saak transform consists of three steps: 1) building the optimal linear subspace approximation with orthonormal bases using the second-order statistics of input vectors, 2) augmenting each transform kernel with its negative, 3) applying the rectified linear unit (ReLU) to the transform output.
Design, Analysis and Application of A Volumetric Convolutional Neural Network
In the design of the VCNN, we propose a feed-forward K-means clustering algorithm to determine the filter number and size at each convolutional layer systematically.
3D Shape Retrieval via Irrelevance Filtering and Similarity Ranking (IF/SR)
The remaining gallery samples are ranked in the SR module using the local feature.
