TITLE:
Dual Channel with Involution for Long-Tailed Visual Recognition
AUTHORS:
Mengxue Li
KEYWORDS:
Long-Tailed Recognition, Deep Neural Network, Dual-Channel Structure, Involution
JOURNAL NAME:
Open Journal of Applied Sciences,
Vol.12 No.4,
April
7,
2022
ABSTRACT: With the
rapid increase of large-scale problems, the
distribution of real-world datasets tends to
be long-tailed. Existing solutions typically involve re-balancing
strategies (i.e., re-sampling and
re-weighting). Although they can significantly promote the classifier learning
of deep networks, they will unexpectedly impair the representative ability of
the learned deep features to a certain extent. Therefore, this paper proposes a
dual-channel learning algorithm with involution neural networks (DC-Invo) to
take care of representation learning and classifier learning concurrently. In
this work, the most important thing is to combine ResNet and involution to
obtain higher classification accuracy because of involution’s wider coverage in
the spatial dimension. The paper conducted extensive experiments on several
benchmark vision tasks including Cifar-LT, Imagenet-LT, and
Places-LT, showing that DC-Invo is able to achieve significant performance
gained on long-tailed datasets.