Learning Representation in Colour Conversion

Arash Akbarinia, Raquel Gil-Rodriguez, Alban Flachot, Matteo Toscani

Keywords: Color representation, VAE, Color space, Unsupervised learning

Abstract: Colours can be represented in an infinite set of spaces highlighting distinct features. Here, we investigated the impact of colour spaces on the encoding capacity of a visual system that is subject to information compression, specifically variational autoencoders (VAEs) where bottlenecks are imposed. To this end, we propose a novel unsupervised task: colour space conversion (ColourConvNets). We trained several instances of VAEs whose input and output are in different colour spaces, e.g. from RGB to CIE L*a*b* (in total five colour spaces were examined). This allowed us to systematically study the influence of input-output colour spaces on the encoding efficiency and learnt representation. Our evaluations demonstrate that ColourConvNets with decorrelated output colour spaces produce higher quality images, also evident in pixel-wise low-level metrics such as colour difference ($\Delta E$), peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). We also assessed the ColourConvNets' capacity to reconstruct the global content in two downstream tasks: image classification (ImageNet) and scene segmentation (COCO). Our results show a 5-10% performance boost for decorrelating ColourConvNets with respect to the baseline network (whose input and output are RGB). Furthermore, we thoroughly analysed the finite embedding space of Vector Quantised VAEs with three different methods (single feature, hue shift and linear transformation). The interpretations reached with these techniques are in agreement suggesting that (i) luminance and chromatic information are encoded in separate embedding vectors, and (ii) the structure of the network's embedding space is determined by the output colour space.

One-sentence Summary: The unsupervised task of colour conversion offers efficient encoding and a method to interpretat colour representation.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=k4I0aTI-MX