Genesis: Generative scene inference and sampling with object-centric latent representations
Generative latent-variable models are emerging as promising tools in robotics and
reinforcement learning. Yet, even though tasks in these domains typically involve distinct …
reinforcement learning. Yet, even though tasks in these domains typically involve distinct …
Genesis-v2: Inferring unordered object representations without iterative refinement
Advances in unsupervised learning of object-representations have culminated in the
development of a broad range of methods for unsupervised object segmentation and …
development of a broad range of methods for unsupervised object segmentation and …
Promising or elusive? unsupervised object segmentation from real-world single images
In this paper, we study the problem of unsupervised object segmentation from single
images. We do not introduce a new algorithm, but systematically investigate the …
images. We do not introduce a new algorithm, but systematically investigate the …
Unsupervised multi-object segmentation by predicting probable motion patterns
We propose a new approach to learn to segment multiple image objects without manual
supervision. The method can extract objects form still images, but uses videos for …
supervision. The method can extract objects form still images, but uses videos for …
Compositional scene representation learning via reconstruction: A survey
Visual scenes are composed of visual concepts and have the property of combinatorial
explosion. An important reason for humans to efficiently learn from diverse visual scenes is …
explosion. An important reason for humans to efficiently learn from diverse visual scenes is …
Posterior control of blackbox generation
Text generation often requires high-precision output that obeys task-specific rules. This fine-
grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we …
grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we …
Graph ode with factorized prototypes for modeling complicated interacting dynamics
This paper studies the problem of modeling interacting dynamical systems, which is critical
for understanding physical dynamics and biological processes. Recent research …
for understanding physical dynamics and biological processes. Recent research …
Benchmarking and Analysis of Unsupervised Object Segmentation from Real-World Single Images
In this paper, we study the problem of unsupervised object segmentation from single
images. We do not introduce a new algorithm, but systematically investigate the …
images. We do not introduce a new algorithm, but systematically investigate the …
Unsupervised video decomposition using spatio-temporal iterative inference
Unsupervised multi-object scene decomposition is a fast-emerging problem in
representation learning. Despite significant progress in static scenes, such models are …
representation learning. Despite significant progress in static scenes, such models are …
PROVIDE: A probabilistic framework for unsupervised video decomposition
Unsupervised multi-object scene decomposition is a fast-emerging problem in
representation learning. Despite significant progress in static scenes, such models are …
representation learning. Despite significant progress in static scenes, such models are …