Seeing through bag-of-visual-word glasses: towards understanding quantization effects in feature extraction methods

08/20/2014
by   Alexander Freytag, et al.
0

Vector-quantized local features frequently used in bag-of-visual-words approaches are the backbone of popular visual recognition systems due to both their simplicity and their performance. Despite their success, bag-of-words-histograms basically contain low-level image statistics (e.g., number of edges of different orientations). The question remains how much visual information is "lost in quantization" when mapping visual features to code words? To answer this question, we present an in-depth analysis of the effect of local feature quantization on human recognition performance. Our analysis is based on recovering the visual information by inverting quantized local features and presenting these visualizations with different codebook sizes to human observers. Although feature inversion techniques are around for quite a while, to the best of our knowledge, our technique is the first visualizing especially the effect of feature quantization. Thereby, we are now able to compare single steps in common image classification pipelines to human counterparts.

READ FULL TEXT

page 5

page 6

page 7

research
03/16/2017

From visual words to a visual grammar: using language modelling for image classification

The Bag--of--Visual--Words (BoVW) is a visual description technique that...
research
09/18/2017

E^2BoWs: An End-to-End Bag-of-Words Model via Deep Convolutional Neural Network

Traditional Bag-of-visual Words (BoWs) model is commonly generated with ...
research
01/17/2011

Introduction to the Bag of Features Paradigm for Image Classification and Retrieval

The past decade has seen the growing popularity of Bag of Features (BoF)...
research
09/30/2018

Improving Bag-of-Visual-Words Towards Effective Facial Expressive Image Classification

Bag-of-Visual-Words (BoVW) approach has been widely used in the recent y...
research
11/30/2020

Where Should We Begin? A Low-Level Exploration of Weight Initialization Impact on Quantized Behaviour of Deep Neural Networks

With the proliferation of deep convolutional neural network (CNN) algori...
research
06/04/2020

Experiments on Paraphrase Identification Using Quora Question Pairs Dataset

We modeled the Quora question pairs dataset to identify a similar questi...
research
06/14/2011

Nested Graph Words for Object Recognition

In this paper, we propose a new, scalable approach for the task of objec...

Please sign up or login with your details

Forgot password? Click here to reset