Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
release_2k4nko7ztvboza2qyqekcmz66e
by
Yixiong Zou, Shanghang Zhang, Ke Chen, Yonghong Tian, Yaowei Wang, José M. F. Moura
2020
Abstract
Few-shot learning (FSL) aims at recognizing novel classes given only few
training samples, which still remains a great challenge for deep learning.
However, humans can easily recognize novel classes with only few samples. A key
component of such ability is the compositional recognition that human can
perform, which has been well studied in cognitive science but is not well
explored in FSL. Inspired by such capability of humans, to imitate humans'
ability of learning visual primitives and composing primitives to recognize
novel classes, we propose an approach to FSL to learn a feature representation
composed of important primitives, which is jointly trained with two parts, i.e.
primitive discovery and primitive enhancing. In primitive discovery, we focus
on learning primitives related to object parts by self-supervision from the
order of image splits, avoiding extra laborious annotations and alleviating the
effect of semantic gaps. In primitive enhancing, inspired by current studies on
the interpretability of deep networks, we provide our composition view for the
FSL baseline model. To modify this model for effective composition, inspired by
both mathematical deduction and biological studies (the Hebbian Learning rule
and the Winner-Take-All mechanism), we propose a soft composition mechanism by
enlarging the activation of important primitives while reducing that of others,
so as to enhance the influence of important primitives and better utilize these
primitives to compose novel classes. Extensive experiments on public benchmarks
are conducted on both the few-shot image classification and video recognition
tasks. Our method achieves the state-of-the-art performance on all these
datasets and shows better interpretability.
In text/plain
format
Archived Files and Locations
application/pdf 5.2 MB
file_ex2fnbe7sbevfjb6f6657fyb3u
|
arxiv.org (repository) web.archive.org (webarchive) |
2005.06047v3
access all versions, variants, and formats of this works (eg, pre-prints)