Quantized Disentangled Representations for Object-Centric Visual Tasks

Daniil Kirilenko, Alexandr Korchemnyi, Alexey Kovalev, Aleksandr Panov

Keywords: quantised representation, disentangled representation, object-centric task

TL;DR: We propose quantised disentangled representations that demonstrate state-of-the art performace in set prediction tasks mong a class of object-centric methods.

Abstract:

Recently, the pre-quantization of image features into discrete latent variables has helped to achieve remarkable results in image modeling. In this paper, we propose a method to learn discrete latent variables applied to object-centric tasks. In our approach, each object is assigned a slot which is represented as a vector generated by sampling from non-overlapping sets of low-dimensional discrete variables.
We empirically demonstrate that embeddings from the learned discrete latent spaces have the disentanglement property. The model is trained with a set prediction and object discovery as downstream tasks. It achieves the state-of-the-art results on the CLEVR dataset among a class of object-centric methods for set prediction task. We also demonstrate manipulation of individual objects in a scene with controllable image generation in the object discovery setting.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning