In this paper, we propose an unsupervised feature learning method called deep binary descriptor with multi-quantization (DBD-MQ) for visual analysis. Existing learning-based binary descriptors such as compact binary face descriptor (CBFD) and DeepBit utilize the rigid sign function for binarization despite of data distributions, which usually suffer from severe quantization loss. In order to address the limitation, we propose a deep multi-quantization network to learn a data-dependent binarization in an unsupervised manner. More specifically, we design a K-Autoencoders (KAEs) network to jointly learn the parameters of feature extractor and the binarization functions under a deep learning framework, so that discriminative binary descriptors can be obtained with a fine-grained multi-quantization. As DBD-MQ simply allocates the same number of quantizers to each real-valued feature dimension ignoring the elementwise diversity of informativeness, we further propose a deep competitive binary descriptor with multi-quantization (DCBD-MQ) method to learn optimal allocation of bits with the fixed binary length in a competitive manner, where informative dimensions gain more bits for complete representation. Moreover, we present a similarity-aware binary encoding strategy based on the earth mover's distance of Autoencoders, so that elements that are quantized into similar Autoencoders will have smaller Hamming distances. Extensive experimental results on six widely-used datasets show that our DBD-MQ and DCBD-MQ outperform most state-of-the-art unsupervised binary descriptors.

中文翻译：

---

使用多量化学习深度二进制描述符


在本文中，我们提出了一种用于视觉分析的无监督特征学习方法，称为多量化深度二进制描述符（DBD-MQ）。现有的基于学习的二进制描述符，例如紧凑二进制面部描述符（CBFD）和 DeepBit，尽管数据分布通常会遭受严重的量化损失，但仍利用刚性符号函数进行二值化。为了解决该限制，我们提出了一种深度多量化网络，以无监督的方式学习依赖于数据的二值化。更具体地说，我们设计了一个K-自动编码器（KAEs）网络来在深度学习框架下共同学习特征提取器的参数和二值化函数，以便可以通过细粒度的多量化获得有判别性的二进制描述符。由于 DBD-MQ 简单地为每个实值特征维度分配相同数量的量化器，忽略了信息量的元素多样性，因此我们进一步提出了一种具有多量化的深度竞争二进制描述符（DCBD-MQ）方法来学习比特的最佳分配以竞争的方式固定二进制长度，其中信息维度获得更多位来完整表示。此外，我们提出了一种基于自动编码器的地球移动距离的相似性感知二进制编码策略，使得量化到相似自动编码器中的元素将具有更小的汉明距离。对六个广泛使用的数据集的广泛实验结果表明，我们的 DBD-MQ 和 DCB-MQ 优于大多数最先进的无监督二进制描述符。