Rotation and Translation Invariant Representation Learning with Implicit Neural Representations

TL;DR

This paper introduces IRL-INR, a method using implicit neural representations and hypernetworks to learn semantic features invariant to image rotations and translations, improving clustering in complex images.

Contribution

The paper presents a novel IRL-INR approach that effectively disentangles semantic representations from image orientation using implicit neural representations and hypernetworks.

Findings

IRL-INR learns disentangled semantic representations on complex images.

IRL-INR achieves state-of-the-art unsupervised clustering results.

Semantic representations from IRL-INR work well with SCAN.

Abstract

In many computer vision applications, images are acquired with arbitrary or random rotations and translations, and in such setups, it is desirable to obtain semantic representations disentangled from the image orientation. Examples of such applications include semiconductor wafer defect inspection, plankton microscope images, and inference on single-particle cryo-electron microscopy (cryo-EM) micro-graphs. In this work, we propose Invariant Representation Learning with Implicit Neural Representation (IRL-INR), which uses an implicit neural representation (INR) with a hypernetwork to obtain semantic representations disentangled from the orientation of the image. We show that IRL-INR can effectively learn disentangled semantic representations on more complex images compared to those considered in prior works and show that these semantic representations synergize well with SCAN to produce state-of-the-art unsupervised clustering results.