
-
Point Cloud Attribute Compression via Successive Subspace Graph Transform
Inspired by the recently proposed successive subspace learning (SSL) pri...
read it
-
PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification
The successive subspace learning (SSL) principle was developed and used ...
read it
-
PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification
A new machine learning methodology, called successive subspace learning ...
read it
-
Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks
A semi-supervised learning framework using the feedforward-designed conv...
read it
-
Ensembles of feedforward-designed convolutional neural networks
An ensemble method that fuses the output decision vectors of multiple fe...
read it
-
Towards Visible and Thermal Drone Monitoring with Convolutional Neural Networks
This paper reports a visible and thermal drone monitoring system that in...
read it
-
Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation
Unsupervised video object segmentation is a crucial application in video...
read it
-
Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation
One major technique debt in video object segmentation is to label the ob...
read it
-
Analysis on Gradient Propagation in Batch Normalized Residual Networks
We conduct mathematical analysis on the effect of batch normalization (B...
read it
-
An Interpretable Generative Model for Handwritten Digit Image Synthesis
An interpretable generative model for handwritten digits synthesis is pr...
read it
-
Interpretable Convolutional Neural Networks via Feedforward Design
The model parameters of convolutional neural networks (CNNs) are determi...
read it
-
Defense Against Adversarial Attacks with Saak Transform
Deep neural networks (DNNs) are known to be vulnerable to adversarial pe...
read it
-
A Deep Learning Approach to Drone Monitoring
A drone monitoring system that integrates deep-learning-based detection ...
read it
-
A Saak Transform Approach to Efficient, Scalable and Robust Handwritten Digits Recognition
An efficient, scalable and robust approach to the handwritten digits rec...
read it
-
On Data-Driven Saak Transform
Being motivated by the multilayer RECOS (REctified-COrrelations on a Sph...
read it
-
Design, Analysis and Application of A Volumetric Convolutional Neural Network
The design, analysis and application of a volumetric convolutional neura...
read it
-
3D Shape Retrieval via Irrelevance Filtering and Similarity Ranking (IF/SR)
A novel solution for the content-based 3D shape retrieval problem using ...
read it