Publication Type

Journal Article

Version

publishedVersion

Publication Date

3-2021

Abstract

Scene labeling or parsing aims to assign pixelwise semantic labels for an input image. Existing CNN-based models cannot leverage the label dependencies, while RNN-based models predict labels within the local context. In this paper, we propose a fast LSTM scene labeling network via structural inference. A minimum spanning tree is used to build the image structure for constructing semantic relationships. This structure allows efficient generation of direct parent-child dependencies for arbitrary levels of superpixels, and thus structural relationships can be learned with LSTM. In particular, we propose a bi-directional recurrent network to model the information flow along the parent-child path. In this way, the recurrent units in both coarse and fine levels can mutually transfer the global and local context information in the entire image structure. The proposed network is extremely fast, and it is 2.5x faster than the state-of-the-art RNN-based models. Extensive expseriments demonstrate that the proposed method provides a significant improvement in learning the label dependencies, and it outperforms state-of-the-art methods on different benchmarks. (C) 2021 Elsevier B.V. All rights reserved.

Keywords

LSTM, Structural inference, Scene labeling

Discipline

Information Security

Research Areas

Information Systems and Management

Publication

Neurocomputing

Volume

442

First Page

317

Last Page

326

ISSN

0925-2312

Identifier

10.1016/j.neucom.2020.12.134

Publisher

Elsevier

Additional URL

https://doi.org/10.1016/j.neucom.2020.12.134

Share

COinS