Self-adaptive neural network training method for image recognition

Abstract

The invention discloses a self-adaptive neural network training method for image recognition. The method comprises the steps: acquiring and preprocessing an image data set; constructing a convolutional neural network model, and setting an adaptive loss function; inputting the preprocessed image data into a convolutional neural network model for forward propagation to obtain a feature vector and a classification layer weight of the image; calculating an adaptive loss function according to the image feature vector and the classification layer weight, and judging whether the convolutional neural network model converges; performing back propagation on the convolutional neural network model according to the adaptive loss function, and updating the weight of the classification layer; and progressively increasing the number of iterations, and updating the adaptive loss function. Compared with a softmax-based classification loss function training method, the method provided by the invention has the advantages that the setting of hyper-parameters is reduced, the convergence speed of the convolutional neural network model can be accelerated, and the image classification and recognition accuracy can be improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an image recognition-oriented adaptive neural network training method. Background technique [0002] The success of convolutional neural networks (CNNs) in image classification and recognition is mainly due to: massive training data, network architecture, and reasonable loss function (loss function). Among them, designing a reasonable loss function according to the characteristics of the data is a key step to improve the image recognition ability. [0003] Softmax function is the most important loss function used in image classification and recognition, and its recognition effect on difficult samples is not good. Through research, it is found that when the intra-class distance of the sample is greater than the inter-class distance, although the softmax loss function can distinguish the inter-class distance, it cannot effectively distinguish the intra-class distance. Th...

AI Technical Summary

Problems solved by technology

Tripletloss belongs to Metric Learning. Compared with softmax, it can easily train large-scale data sets without being limited by video memory. It can make the distance between samples of the same type as small as possible and the distance between samples of different types as large as possible. The disadvantages It is too much attention to the local area, which makes it difficult to converge and the training time is too long

[0004] Image classification and recognition tasks mainly use softmax and its deformation as the loss function, but this type of loss function requires a large amount of data and manual parameter adjustment during training, especially when facing difficult samples, it is difficult to achieve good classification and recognition results

Images