Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning
release_kh2u4ukuxnh2phlovnswnf52mq
by
Chaoqun Wang, Xuejin Chen, Shaobo Min, Xiaoyan Sun, Houqiang Li
2021
Abstract
Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by
learning transferable image representations. Existing methods find that, by
aligning image representations with corresponding semantic labels, the
semantic-aligned representations can be transferred to unseen categories.
However, supervised by only seen category labels, the learned semantic
knowledge is highly task-specific, which makes image representations biased
towards seen categories. In this paper, we propose a novel Dual-Contrastive
Embedding Network (DCEN) that simultaneously learns task-specific and
task-independent knowledge via semantic alignment and instance discrimination.
First, DCEN leverages task labels to cluster representations of the same
semantic category by cross-modal contrastive learning and exploring
semantic-visual complementarity. Besides task-specific knowledge, DCEN then
introduces task-independent knowledge by attracting representations of
different views of the same image and repelling representations of different
images. Compared to high-level seen category supervision, this instance
discrimination supervision encourages DCEN to capture low-level visual
knowledge, which is less biased toward seen categories and alleviates the
representation bias. Consequently, the task-specific and task-independent
knowledge jointly make for transferable representations of DCEN, which obtains
averaged 4.1% improvement on four public benchmarks.
In text/plain
format
Archived Files and Locations
application/pdf 1.1 MB
file_4ne25nwutzbhhp7yo7wk2khu2q
|
arxiv.org (repository) web.archive.org (webarchive) |
2104.01832v1
access all versions, variants, and formats of this works (eg, pre-prints)