GENESIS-V2: inferring unordered object representations without iterative refinement

• DOI: 10.48550/arxiv.2104.09958
• Publication Date: 2021-01-01
• Authors: Engelcke, M; Parker Jones, OP; Posner, I
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Statistics - Machine Learning; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 0202 electrical engineering, electronic engineering, information engineering; Machine Learning (stat.ML); 02 engineering and technology; Machine Learning (cs.LG)

Advances in unsupervised learning of object-representations have culminated in the development of a broad range of methods for unsupervised object segmentation and interpretable object-centric scene generation. These methods, however, are limited to simulated and real-world datasets with limited visual complexity. Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori initialisation of a fixed number of object representations. In contrast to established paradigms, this work proposes an embedding-based approach in which embeddings of pixels are clustered in a differentiable fashion using a stochastic stick-breaking process. Similar to iterative refinement, this clustering procedure also leads to randomly ordered object representations, but without the need of initialising a fixed number of clusters a priori. This is used to develop a new model, GENESIS-v2, which can infer a variable number of object representations without using RNNs or iterative refinement. We show that GENESIS-v2 performs strongly in comparison to recent baselines in terms of unsupervised image segmentation and object-centric scene generation on established synthetic datasets as well as more complex real-world datasets.<br/>NeurIPS 2021 camera-ready version; 26 pages, 19 figures<br/>