Inference via Sparse Coding in a Hierarchical Vision Model

08/03/2021
by   Joshua Bowren, et al.
8

Sparse coding has been incorporated in models of the visual cortex for its computational advantages and connection to biology. But how the level of sparsity contributes to performance on visual tasks is not well understood. In this work, sparse coding has been integrated into an existing hierarchical V2 model (Hosoya and Hyvärinen, 2015), but replacing the Independent Component Analysis (ICA) with an explicit sparse coding in which the degree of sparsity can be controlled. After training, the sparse coding basis functions with a higher degree of sparsity resembled qualitatively different structures, such as curves and corners. The contributions of the models were assessed with image classification tasks, including object classification, and tasks associated with mid-level vision including figure-ground classification, texture classification, and angle prediction between two line stimuli. In addition, the models were assessed in comparison to a texture sensitivity measure that has been reported in V2 (Freeman et al., 2013), and a deleted-region inference task. The results from the experiments show that while sparse coding performed worse than ICA at classifying images, only sparse coding was able to better match the texture sensitivity level of V2 and infer deleted image regions, both by increasing the degree of sparsity in sparse coding. Higher degrees of sparsity allowed for inference over larger deleted image regions. The mechanism that allows for this inference capability in sparse coding is described here.

READ FULL TEXT

page 8

page 9

page 14

page 16

page 17

page 19

page 23

page 24

research
08/30/2014

Sparse Coding on Symmetric Positive Definite Manifolds using Bregman Divergences

This paper introduces sparse coding and dictionary learning for Symmetri...
research
08/14/2021

A Sparse Coding Interpretation of Neural Networks and Theoretical Implications

Neural networks, specifically deep convolutional neural networks, have a...
research
10/26/2017

Image Compression: Sparse Coding vs. Bottleneck Autoencoders

Bottleneck autoencoders have been actively researched as a solution to i...
research
02/03/2020

Effect of top-down connections in Hierarchical Sparse Coding

Hierarchical Sparse Coding (HSC) is a powerful model to efficiently repr...
research
01/24/2021

Exploitation of Image Statistics with Sparse Coding in the Case of Stereo Vision

The sparse coding algorithm has served as a model for early processing i...
research
01/05/2015

Sparse Deep Stacking Network for Image Classification

Sparse coding can learn good robust representation to noise and model mo...
research
06/01/2021

Reconciliation of Statistical and Spatial Sparsity For Robust Image and Image-Set Classification

Recent image classification algorithms, by learning deep features from l...

Please sign up or login with your details

Forgot password? Click here to reset