使用深度监督哈希的快速多标签图像检索
首发时间:2018-02-14
摘要:现在存在的大部分监督哈希是将手工提取的特征转换为哈希值,然后根据图像标签为监督信息得到损失函数,但是手工提取特征以及不完全考虑所有损失的损失函数会降低检索精度。监督哈希算法主要目的是通过训练数据以及数据的标签提升数据与相应哈希的相似度,从而提高检索的相似度。本文提出了一个新的监督哈希算法,将每个图像的多标签转换为二进制向量,通过汉明距离得到成对图像的相似度,放入损失函数中作为监督信息,加上图像特征量化为哈希码时的量化误差以及所有图像哈希码与平衡值的差值,结合以上所有部分生成损失函数,进行网络训练。实验结果显示本文的方法在检索精度上比现有的方法有所提升。
For information in English, please click here
Deep Supervised Hashing for Fast Multi-label Image Retrieval
Abstract:Most of The existing Hashing methods is mapping the hand extracted features to binary code, and designing the loss function with the label of images. However, hand-crafted features and inadequacy considering all the loss of the network will reduce the retrieval accuracy. Supervised hashing method improves the similarity between sample and hash code by training data and labels of image. In this paper, we propose a novel deep hashing method which is combine the objective function with pairwise label which is produced by the hamming distance between the label binary vector of images, quantization error and the loss aaaaof hashing code between the balanced value as loss function to train network. The experimental results show that the proposed method is more accurate than most of current restoration mDeep Supervised Hashing for Fast Multi-label Image Retrievalethods.
Keywords: hashing function loss function CNN label
基金:
引用
No.****
同行评议
共计0人参与
勘误表
使用深度监督哈希的快速多标签图像检索
评论
全部评论0/1000