Material Classification in the Wild: Do Synthesized Training Data Generalise Better than Real-World Training Data?

11/09/2017
by   Grigorios Kalliatakis, et al.
0

We question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than real-world data. Experimental results on three challenging real-world material databases show that the best performing pre-trained convolutional neural network (CNN) architectures can achieve up to 91.03 scenarios. We demonstrate that synthesized data achieve an improvement on mean average precision when used as training data and in conjunction with pre-trained CNN architectures, which spans from 5 widely used material databases of real-world images.

READ FULL TEXT
research
03/12/2017

Evaluating Deep Convolutional Neural Networks for Material Classification

Determining the material category of a surface from an image is a demand...
research
11/18/2018

Deep Learning with Inaccurate Training Data for Image Restoration

In many applications of deep learning, particularly those in image resto...
research
01/17/2021

Estimating informativeness of samples with Smooth Unique Information

We define a notion of information that an individual sample provides to ...
research
04/08/2020

A Deep Learning Approach for Determining Effects of Tuta Absoluta in Tomato Plants

Early quantification of Tuta absoluta pest's effects in tomato plants is...
research
10/07/2019

Task-Adaptive Incremental Learning for Intelligent Edge Devices

Convolutional Neural Networks (CNNs) are used for a wide range of image-...
research
01/27/2022

TableQuery: Querying tabular data with natural language

This paper presents TableQuery, a novel tool for querying tabular data u...
research
04/01/2018

SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data

State-of-the-art techniques of artificial intelligence, in particular de...

Please sign up or login with your details

Forgot password? Click here to reset