.png){kind=icon}
返回
Multi-Level Second-Order Few-Shot Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2022.3142955.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We propose a Multi-level Second-order (MlSo) few-shot learning network for supervised or unsupervised few-shot image classification and few-shot action recognition. We leverage so-called power-normalized second-order base learner streams combined with features that express multiple levels of visual abstraction, and we use self-supervised discriminating mechanisms. As Second-order Pooling (SoP) is popular in image recognition, we employ its basic element-wise variant in our pipeline. The goal of multi-level feature design is to extract feature representations at different layer-wise levels of CNN, realizing several levels of visual abstraction to achieve robust few-shot learning. As SoP can handle convolutional feature maps of varying spatial sizes, we also introduce image inputs at multiple spatial scales into MlSo. To exploit the discriminative information from multi-level and multi-scale features, we develop a Feature Matching (FM) module that reweights their respective branches. We also introduce a self-supervised step, which is a discriminator of the spatial level and the scale of abstraction. Our pipeline is trained in an end-to-end manner. With a simple architecture, we demonstrate respectable results on standard datasets such as Omniglot, mini-ImageNet, tiered-ImageNet, Open MIC, fine-grained datasets such as CUB Birds, Stanford Dogs and Cars, and action recognition datasets such as HMDB51, UCF101, and mini-MIT.
Keyword:
Task analysis
Pipelines
Image recognition
Visualization
Feature extraction
Training
Streaming media
Few-shot learning
second-order statistics
image classification
action recognition
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
分享收藏Bäcklund transformation, nonlinear superposition formula and solutions of the Calogero equation
PREAI
分享收藏
查看更多内容