Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization
Preprint
Abstract
In this project we attempt to make slot-based models with an image reconstruction objective competitive with those that use a feature reconstruction objective on real world datasets. We propose a loss-based approach to constricting the bottleneck of slot-based models, allowing larger-capacity encoder networks to be used with Slot Attention without producing degenerate stripe-shaped masks. We find that our proposed method offers an improvement over the baseline Slot Attention model but does not reach the performance of \dinosaur on the COCO2017 dataset. Throughout this project, we confirm the superiority of a feature reconstruction objective over an image reconstruction objective and explore the role of the architectural bottleneck in slot-based models.Keywords
All Related Versions
This publication has 3 references indexed in Scilit:
- Toward Unsupervised Visual Reasoning: Do Off-the-Shelf Features Know How to Reason?IEEE Access, 2024
- Inductive biases for deep learning of higher-level cognitionProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2022
- Exploring Simple Siamese Representation Learning2021