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

Anna Foix Romero, Craig Russell, Alexander Krull, Virginie Uhlmann

Keywords: shape quantification, shape descriptors, VAE, generative model, representation learning, microscopy

TL;DR: ShapeEmbed is a self-supervised method using Euclidean distance matrices to encode the shape of objects in 2D images in a way that is robust to shape-preserving geometric transformations

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.

Primary Area: Machine learning for sciences (e.g. climate, health, life sciences, physics, social sciences)

Submission Number: 10486