A Few Shot Image Ensemble Classification Algorithm Based on Meta-Learning
Peng He, Qun Liu · 2021
Aiming at the problem of decreased accuracy in model classification resulting from the drift of data types in the few shot image classifications, this paper proposes a few shot image ensemble classification method based on meta-learning. Applying feature extraction network on the basis of attention mechanism to extract the features in the image, this method is able to input the feature vector extracted to meta-learner and generate the weight parameter of similarity measurement network in the corresponding channel herewith. And then integrate the similarity distance calculated by multiple weak classifiers in all channels to get the classification results of target sample. The experiment on the miniImageNet data set indicates that the tasks on the 5way1shot and 20way1shot have improved 11.8% and 13.41% respectively, corresponding to the control method, and that when applying the model parameters trained by MiniImageNet data set to perform the test on the CUB200 and Clatech101 data set, the classification accuracy of ECML proposed here is also higher than it of control model. Thus it can be seen that to generate a similarity measurement network by building a meta-learner on a meta-task not only improves the model's generalization ability, but also effectively solves the problem of performance degradation of few shot image classification when the data sample type drifts.