ShapeEmbed: a self-supervised learning framework for 2D contour quantification

TL;DR

ShapeEmbed is a self-supervised framework that encodes 2D object contours into invariant shape descriptors, outperforming traditional methods and aiding biological image analysis.

Contribution

Introduces ShapeEmbed, a novel self-supervised learning method for invariant 2D shape representation using Euclidean distance matrices.

Findings

Outperforms existing autoencoder-based shape descriptors.

Achieves higher accuracy in shape classification tasks.

Effective for biological and natural image analysis.

Abstract

The shape of objects is an important source of visual information in a wide range of applications. One of the core challenges of shape quantification is to ensure that the extracted measurements remain invariant to transformations that preserve an object's intrinsic geometry, such as changing its size, orientation, and position in the image. In this work, we introduce ShapeEmbed, a self-supervised representation learning framework designed to encode the contour of objects in 2D images, represented as a Euclidean distance matrix, into a shape descriptor that is invariant to translation, scaling, rotation, reflection, and point indexing. Our approach overcomes the limitations of traditional shape descriptors while improving upon existing state-of-the-art autoencoder-based approaches. We demonstrate that the descriptors learned by our framework outperform their competitors in shape classification tasks on natural and biological images. We envision our approach to be of particular relevance to biological imaging applications.