DeepAI AI Chat
Log In Sign Up

Learning Illuminant Estimation from Object Recognition

by   Marco Buzzelli, et al.
Università degli Studi di Milano-Bicocca

In this paper we present a deep learning method to estimate the illuminant of an image. Our model is not trained with illuminant annotations, but with the objective of improving performance on an auxiliary task such as object recognition. To the best of our knowledge, this is the first example of a deep learning architecture for illuminant estimation that is trained without ground truth illuminants. We evaluate our solution on standard datasets for color constancy, and compare it with state of the art methods. Our proposal is shown to outperform most deep learning methods in a cross-dataset evaluation setup, and to present competitive results in a comparison with parametric solutions.


page 3

page 4


Saliency for free: Saliency prediction as a side-effect of object recognition

Saliency is the perceptual capacity of our visual system to focus our at...

YCB-M: A Multi-Camera RGB-D Dataset for Object Recognition and 6DoF Pose Estimation

While a great variety of 3D cameras have been introduced in recent years...

Fit to Measure: Reasoning about Sizes for Robust Object Recognition

Service robots can help with many of our daily tasks, especially in thos...

Deep Learning for Single-View Instance Recognition

Deep learning methods have typically been trained on large datasets in w...

Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies

Despite impressive advances in object-recognition, deep learning systems...

Evolving Deep Neural Networks

The success of deep learning depends on finding an architecture to fit t...

Knock-Knock: Acoustic Object Recognition by using Stacked Denoising Autoencoders

This paper presents a successful application of deep learning for object...