Deep semantic hashing of 3D geometric features for efficient 3D model retrieval
Deep semantic hashing of 3D geometric features for efficient 3D model retrieval
复制标题
DOI：
10.1145/3095140.3095148
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
T. Furuya;Ryutarou Ohbuchi
中科院分区：
文献类型：
--
作者：
T. Furuya;Ryutarou Ohbuchi
随着3D模型数据库规模的增加，除了准确性之外，其搜索速度也变得非常重要。实现快速搜索的一种方法是使用紧凑的 3D 形状特征，其比较成本非常小。通过散列对实值特征向量进行二值化是获得这种紧凑特征向量的一种方法。以前通过哈希生成二值化 3D 模型特征的算法由两个互不相连的阶段组成；手工制作的实值 3D 形状特征提取，然后哈希为二进制代码。然而，这种划分方法会导致二进制代码不太理想，因为这两个阶段是独立优化的。本文提出了一种称为二值化深度局部特征聚合网络（BDLAN）的深度语义哈希算法，该算法通过哈希联合优化每个 3D 模型的实值特征提取及其平坦化。 BDLAN 训练最大限度地减少了二值化引起的量化误差。然而，仅此约束通常会将实值特征映射到汉明空间中最接近的二进制代码，这是非最优的局部最小值。为了缓解这个问题，我们添加了一个简单的正则化，称为二进制代码的概率位反转 (PBI)。对所提出算法的实验评估表明，与现有的采用实值特征的 3D 模型检索算法相比，该算法具有更高的效率和有竞争力的准确性。
As the scale of 3D model databases increase, speed, in addition to accuracy, of its search becomes very important. One way to achieve fast search is to use a compact 3D shape feature whose cost of comparison is very small. Binarization of a real-valued feature vector, via hashing, is a way to obtain such compact feature vector. Previous algorithms for producing binarized 3D model features via hashing consisted of two disconnected stages; handcrafted real-valued 3D shape feature extraction followed by hashing into binary code. This compartmentalized approach, however, leads to less-than optimal binary codes, as these two stages are optimized independently. This paper proposes a deep semantic hashing algorithm called Binarized Deep Local feature Aggregation Network (BDLAN) which jointly optimizes real-valued feature extraction per 3D model and its banarization via hashing. BDLAN training minimizes quantization error caused by binarization. However, this constraint alone often maps real-valued features to their nearest binary codes in Hamming space, which are nonoptimal local minima. To alleviate the issue, we add a simple regularization called Probabilistic Bit Inversion (PBI) of binary codes. Experimental evaluation of the proposed algorithms demonstrates superior efficiency and competitive accuracy to the existing 3D model retrieval algorithms employing real-valued features.