The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes. In this paper, we propose a generative latent variable model, called SPACE, that provides a unified probabilistic modeling framework that combines the best of spatial-attention and scene-mixture approaches. SPACE can explicitly provide factorized object representations for foreground objects while also decomposing background segments of complex morphology. Previous models are good at either of these, but not both. SPACE also resolves the scalability problems of previous methods by incorporating parallel spatial-attention and thus is applicable to scenes with a large number of objects without performance degradations. We show through experiments on Atari and 3D-Rooms that SPACE achieves the above properties consistently in comparison to SPAIR, IODINE, and GENESIS. Results of our experiments can be found on our project website: https://sites.google.com/view/space-project-page

No abstract

In this paper, we address the problem of indoor semantic segmentation by incorporating the depth information into the convolutional neural network and conditional random field of a neural network architecture. The architecture combines a RGB-D fully convolutional neural network (DFCN) with a depth-sensitive fully-connected conditional random field (DCRF). In the DFCN module, the depth information is incorporated into the early layers using a fusion structure which is followed by several dilated convolution layers for contextual reasoning. Later in the DCRF module, a depth-sensitive fully-connected conditional random field (DCRF) is proposed and combined with the previous DFCN output to refine the preliminary result. Comparative experiments show that the proposed DFCN-DCRF architecture achieves competitive performance compared with state-of-the-art methods.

No abstract

No abstract