Object-centric architectures enable efficient causal representation learning
ICLR 2024(2023)
摘要
Causal representation learning has showed a variety of settings in which we
can disentangle latent variables with identifiability guarantees (up to some
reasonable equivalence class). Common to all of these approaches is the
assumption that (1) the latent variables are represented as $d$-dimensional
vectors, and (2) that the observations are the output of some injective
generative function of these latent variables. While these assumptions appear
benign, we show that when the observations are of multiple objects, the
generative function is no longer injective and disentanglement fails in
practice. We can address this failure by combining recent developments in
object-centric learning and causal representation learning. By modifying the
Slot Attention architecture arXiv:2006.15055, we develop an object-centric
architecture that leverages weak supervision from sparse perturbations to
disentangle each object's properties. This approach is more data-efficient in
the sense that it requires significantly fewer perturbations than a comparable
approach that encodes to a Euclidean space and we show that this approach
successfully disentangles the properties of a set of objects in a series of
simple image-based disentanglement experiments.
更多查看译文
关键词
object centric learning,representation learning,disentanglement,weakly supervised learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要