.png){kind=icon}
.png){kind=icon}
Return
Sample-Centric Feature Generation for Semi-Supervised Few-Shot Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2022.3154938.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Semi-supervised few-shot learning aims to improve the model generalization ability by means of both limited labeled data and widely-available unlabeled data. Previous works attempt to model the relations between the few-shot labeled data and extra unlabeled data, by performing a label propagation or pseudo-labeling process using an episodic training strategy. However, the feature distribution represented by the pseudo-labeled data itself is coarse-grained, meaning that there might be a large distribution gap between the pseudo-labeled data and the real query data. To this end, we propose a sample-centric feature generation (SFG) approach for semi-supervised few-shot image classification. Specifically, the few-shot labeled samples from different classes are initially trained to predict pseudo-labels for the potential unlabeled samples. Next, a semi-supervised meta-generator is utilized to produce derivative features centering around each pseudo-labeled sample, enriching the intra-class feature diversity. Meanwhile, the sample-centric generation constrains the generated features to be compact and close to the pseudo-labeled sample, ensuring the inter-class feature discriminability. Further, a reliability assessment (RA) metric is developed to weaken the influence of generated outliers on model learning. Extensive experiments validate the effectiveness of the proposed feature generation approach on challenging one- and few-shot image classification benchmarks.
Keywords:
Task analysis
Data models
Measurement
Training
Semantics
Adaptation models
Benchmark testing
Few-shot learning
feature generation
image classification
sample-centric
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W