Unsupervised Object-Centric Learning with Bi-Level Optimized Query Slot Attention

by   Baoxiong Jia, et al.

The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning. In the recent culmination of unsupervised object-centric learning, the Slot-Attention module has played an important role with its simple yet effective design and fostered many powerful variants. These methods, however, have been exceedingly difficult to train without supervision and are ambiguous in the notion of object, especially for complex natural scenes. In this paper, we propose to address these issues by (1) initializing Slot-Attention modules with learnable queries and (2) optimizing the model with bi-level optimization. With simple code adjustments on the vanilla Slot-Attention, our model, Bi-level Optimized Query Slot Attention, achieves state-of-the-art results on both synthetic and complex real-world datasets in unsupervised image segmentation and reconstruction, outperforming previous baselines by a large margin ( 10 We provide thorough ablative studies to validate the necessity and effectiveness of our design. Additionally, our model exhibits excellent potential for concept binding and zero-shot learning. We hope our effort could provide a single home for the design and learning of slot-based models and pave the way for more challenging tasks in object-centric learning. Our implementation is publicly available at https://github.com/Wall-Facer-liuyu/BO-QSA.


page 7

page 19

page 20

page 21

page 22

page 23

page 24

page 25


Slot-VAE: Object-Centric Scene Generation with Slot Attention

Slot attention has shown remarkable object-centric representation learni...

Unsupervised Conditional Slot Attention for Object Centric Learning

Extracting object-level representations for downstream reasoning tasks i...

Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos

Self-supervised methods have shown remarkable progress in learning high-...

Solving Reasoning Tasks with a Slot Transformer

The ability to carve the world into useful abstractions in order to reas...

Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization

In this project we attempt to make slot-based models with an image recon...

Complex-Valued Autoencoders for Object Discovery

Object-centric representations form the basis of human perception and en...

Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior

The aim of object-centric vision is to construct an explicit representat...

Please sign up or login with your details

Forgot password? Click here to reset