基于延拓的三值哈希码深度学习
Deep Learning to Ternary Hash Codes by Continuation
摘要:
最近,人们已经观察到,{0,1,-1}-三进制码,简单地从深特征通过硬阈值生成,往往优于{-1,1}-二进制码在图像检索。为了获得更好的三进制码,我们首次提出通过向网络附加平滑函数来联合学习特征与代码。在训练过程中,该函数可以通过延拓方法进化成非光滑的三元函数。该方法避免了直接训练离散函数的困难,减少了三进制码的量化误差。实验表明,生成的代码确实能达到较高的检索准确率。
英文摘要:
Recently, it has been observed that {0,1,-1}-ternary codes which are simply generated from deep features by hard thresholding, tend to outperform {-1,1}-binary codes in image retrieval. To obtain better ternary codes, we for the first time propose to jointly learn the features with the codes by appending a smoothed function to the networks. During training, the function could evolve into a non-smoothed ternary function by a continuation method. The method circumvents the difficulty of directly training discrete functions and reduces the quantization errors of ternary codes. Experiments show that the generated codes indeed could achieve higher retrieval accuracy.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。