Curriculum Learning for Multi-Task Classification of Visual Attributes
release_b6zugyrmhzcpphuvmok5tkyfyy
by
Nikolaos Sarafianos, Theodore Giannakopoulos, Christophoros Nikou,
Ioannis A. Kakadiaris
2017
Abstract
Visual attributes, from simple objects (e.g., backpacks, hats) to
soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful
representational approach for many applications such as image description and
human identification. In this paper, we introduce a novel method to combine the
advantages of both multi-task and curriculum learning in a visual attribute
classification framework. Individual tasks are grouped based on their
correlation so that two groups of strongly and weakly correlated tasks are
formed. The two groups of tasks are learned in a curriculum learning setup by
transferring the acquired knowledge from the strongly to the weakly correlated.
The learning process within each group though, is performed in a multi-task
classification setup. The proposed method learns better and converges faster
than learning all the tasks in a typical multi-task learning paradigm. We
demonstrate the effectiveness of our approach on the publicly available, SoBiR,
VIPeR and PETA datasets and report state-of-the-art results across the board.
In text/plain
format
Archived Files and Locations
application/pdf 711.3 kB
file_xkusvw7y75guhm3tjv2ab43sze
|
arxiv.org (repository) web.archive.org (webarchive) |
1708.08728v1
access all versions, variants, and formats of this works (eg, pre-prints)