Toronto Metropolitan University
Browse
Harley_Adam_W.pdf (9.41 MB)

Segmentation-aware convolutional nets

Download (9.41 MB)
thesis
posted on 2021-05-23, 18:43 authored by Adam W. Harley
This thesis introduces a method to both obtain segmentation information and integrate it uniformly within a convolutional neural network (CNN). This counter-acts the tendency of CNNs to produce smooth predictions, which is undesirable for pixel-wise prediction tasks, such as semantic segmentation. The segmentation information is obtained by a form of metric learning, where a CNN learns to compute pixel embeddings that reflect whether any pair of pixels is likely to belong to the same region. This information is then used within a larger network, to replace all convolutions with foreground-focused convolutions, where the foreground is determined adaptively at each image point by local embeddings. The resulting network is called a segmentation-aware CNN, because the network can change its behaviour at each image location according to local segmentation cues. The proposed method yields systematic improvements on a standard semantic segmentation benchmark when compared to a strong baseline.

History

Language

eng

Degree

  • Master of Science

Program

  • Computer Science

Granting Institution

Ryerson University

LAC Thesis Type

  • Thesis

Usage metrics

    Computer Science (Theses)

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC