Multiscale Adaptive Representation of Signals: I. The Basic Framework

07/17/2015
by   Cheng Tai, et al.
0

We introduce a framework for designing multi-scale, adaptive, shift-invariant frames and bi-frames for representing signals. The new framework, called AdaFrame, improves over dictionary learning-based techniques in terms of computational efficiency at inference time. It improves classical multi-scale basis such as wavelet frames in terms of coding efficiency. It provides an attractive alternative to dictionary learning-based techniques for low level signal processing tasks, such as compression and denoising, as well as high level tasks, such as feature extraction for object recognition. Connections with deep convolutional networks are also discussed. In particular, the proposed framework reveals a drawback in the commonly used approach for visualizing the activations of the intermediate layers in convolutional networks, and suggests a natural alternative.

READ FULL TEXT

page 9

page 19

page 20

page 24

page 25

page 27

page 31

research
06/14/2018

Finding GEMS: Multi-Scale Dictionaries for High-Dimensional Graph Signals

Modern data introduces new challenges to classic signal processing appro...
research
01/31/2016

Trainlets: Dictionary Learning in High Dimensions

Sparse representations has shown to be a very powerful model for real wo...
research
05/21/2020

When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data

We present a new Deep Dictionary Learning and Coding Network (DDLCN) for...
research
01/16/2013

Jitter-Adaptive Dictionary Learning - Application to Multi-Trial Neuroelectric Signals

Dictionary Learning has proven to be a powerful tool for many image proc...
research
02/05/2018

Weakly-supervised Dictionary Learning

We present a probabilistic modeling and inference framework for discrimi...
research
01/26/2019

Distributed Convolutional Dictionary Learning (DiCoDiLe): Pattern Discovery in Large Images and Signals

Convolutional dictionary learning (CDL) estimates shift invariant basis ...
research
12/03/2018

On learning with shift-invariant structures

We describe new results and algorithms for two different, but related, p...

Please sign up or login with your details

Forgot password? Click here to reset