Learning to hash has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval, due to its computation efficiency and retrieval quality. Deep learning to hash, which improves retrieval quality by end-to-end representation learning and hash encoding, has received increasing attention recently. Subject to the vanishing gradient difficulty in the optimization with binary activations, existing deep learning to hash methods need to first learn continuous representations and then generate binary hash codes in a separated binarization step, which suffer from substantial loss of retrieval quality. This paper presents HashNet, a novel deep architecture for deep learning to hash by continuation method, which learns exactly binary hash codes from imbalanced similarity data where the number of similar pairs is much smaller than the number of dissimilar pairs. The key idea is to attack the vanishing gradient problem in optimizing deep networks with non-smooth binary activations by continuation method, in which we begin from learning an easier network with smoothed activation function and let it evolve during the training, until it eventually goes back to being the original, difficult to optimize, deep network with the sign activation function. Comprehensive empirical evidence shows that HashNet can generate exactly binary hash codes and yield state-of-the-art multimedia retrieval performance on standard benchmarks.

HashNet是一种基于连续化方法具有收敛保证的新型深度学习哈希结构，它从不平衡的相似性数据中学习准确的二进制哈希码，在标准测试中可产生最先进的多媒体检索性能。

HashNet: 基于连续方法的深度哈希学习