Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer
Shenghan Su, Lin Gu, Yue Yang, Zenghui Zhang, Tatsuya, Harada

TL;DR
This paper introduces CQFormer, a novel transformer-based colour quantisation method that discovers colour naming systems optimized for recognition efficiency, mirroring linguistic evolution patterns and improving image compression and recognition performance.
Contribution
We propose CQFormer, a transformer model that quantises colour space while balancing recognition accuracy and perceptual colour structure, revealing evolution patterns similar to human languages.
Findings
Discovered colour systems show patterns similar to human language colour terms.
Achieved high recognition accuracy with extremely low bit-rate colour quantisation.
Enhanced image compression while maintaining high-level recognition performance.
Abstract
The long-standing theory that a colour-naming system evolves under dual pressure of efficient communication and perceptual mechanism is supported by more and more linguistic studies, including analysing four decades of diachronic data from the Nafaanra language. This inspires us to explore whether machine learning could evolve and discover a similar colour-naming system via optimising the communication efficiency represented by high-level recognition performance. Here, we propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining the accuracy of machine recognition on the quantised images. Given an RGB image, Annotation Branch maps it into an index map before generating the quantised image with a colour palette; meanwhile the Palette Branch utilises a key-point detection way to find proper colours in the palette among the whole colour space.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRemote-Sensing Image Classification
