Rotation and Translation Invariant Representation Learning with Implicit Neural Representations
This addresses the need for orientation-invariant representations in applications like semiconductor inspection and cryo-EM, offering an incremental improvement over existing methods.
The paper tackles the problem of learning semantic representations from images with arbitrary rotations and translations, proposing IRL-INR to disentangle orientation from semantics. It shows that this method works on more complex images than prior works and achieves state-of-the-art unsupervised clustering results when combined with SCAN.
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.