Visual Boundary Knowledge Translation for Foreground Segmentation
When confronted with objects of unknown types in an image, humans can effortlessly and precisely tell their visual boundaries. This recognition mechanism and underlying generalization capability seem to contrast to state-of-the-art image segmentation networks that rely on large-scale category-aware...
Gespeichert in:
Hauptverfasser: | , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | When confronted with objects of unknown types in an image, humans can
effortlessly and precisely tell their visual boundaries. This recognition
mechanism and underlying generalization capability seem to contrast to
state-of-the-art image segmentation networks that rely on large-scale
category-aware annotated training samples. In this paper, we make an attempt
towards building models that explicitly account for visual boundary knowledge,
in hope to reduce the training effort on segmenting unseen categories.
Specifically, we investigate a new task termed as Boundary Knowledge
Translation (BKT). Given a set of fully labeled categories, BKT aims to
translate the visual boundary knowledge learned from the labeled categories, to
a set of novel categories, each of which is provided only a few labeled
samples. To this end, we propose a Translation Segmentation Network
(Trans-Net), which comprises a segmentation network and two boundary
discriminators. The segmentation network, combined with a boundary-aware
self-supervised mechanism, is devised to conduct foreground segmentation, while
the two discriminators work together in an adversarial manner to ensure an
accurate segmentation of the novel categories under light supervision.
Exhaustive experiments demonstrate that, with only tens of labeled samples as
guidance, Trans-Net achieves close results on par with fully supervised
methods. |
---|---|
DOI: | 10.48550/arxiv.2108.00379 |