Parallelized Spatiotemporal Binding

arXiv:2402.17077v1 Announce Type: new
Abstract: While modern best practices advocate for scalable architectures that support long-range interactions, object-centric models are yet to fully embrace these architectures. In particular, existing object-centric models for handling sequential inputs, due to their reliance on RNN-based implementation, show poor stability and capacity and are slow to train on long sequences. We introduce Parallelizable Spatiotemporal Binder or PSB, the first temporally-parallelizable slot learning architecture for sequential inputs. Unlike conventional RNN-based approaches, PSB produces object-centric representations, known …

abstract architectures arxiv best practices capacity cs.cv cs.lg implementation inputs interactions modern practices reliance rnn scalable show stability support train type