Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN
Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN
复制标题
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Shupeng Su;Chao Zhang-;Kai Han;Yonghong Tian
中科院分区：
文献类型：
--
作者：
Shupeng Su;Chao Zhang-;Kai Han;Yonghong Tian
为了将输入转换为二进制代码，散列算法由于其计算和存储效率而被广泛用于大规模图像集的近似最近邻搜索。深度哈希通过将哈希编码与深度神经网络相结合，进一步提高了检索质量。然而，深度哈希的一个主要困难在于对网络输出施加的离散约束，这通常使得优化NP困难。在这项工作中，我们采用贪婪的原则来解决这个NP困难的问题，迭代更新网络的可能的最佳离散解在每次迭代。设计了一个哈希编码层来实现我们的方法，该方法在前向传播中严格使用符号函数来保持离散约束，而在后向传播中，梯度被完整地传输到前层以避免梯度消失。除了理论推导，我们提供了一个新的视角来可视化和理解我们的算法的有效性和效率。基准数据集上的实验表明，我们的计划优于国家的最先进的哈希方法在监督和无监督的任务。
To convert the input into binary code, hashing algorithm has been widely used for approximate nearest neighbor search on large-scale image sets due to its computation and storage efficiency. Deep hashing further improves the retrieval quality by combining the hash coding with deep neural network. However, a major difficulty in deep hashing lies in the discrete constraints imposed on the network output, which generally makes the optimization NP hard. In this work, we adopt the greedy principle to tackle this NP hard problem by iteratively updating the network toward the probable optimal discrete solution in each iteration. A hash coding layer is designed to implement our approach which strictly uses the sign function in forward propagation to maintain the discrete constraints, while in back propagation the gradients are transmitted intactly to the front layer to avoid the vanishing gradients. In addition to the theoretical derivation, we provide a new perspective to visualize and understand the effectiveness and efficiency of our algorithm. Experiments on benchmark datasets show that our scheme outperforms state-of-the-art hashing methods in both supervised and unsupervised tasks.