Deep Momentum Uncertainty Hashing

by   Chaoyou Fu, et al.

Discrete optimization is one of the most intractable problems in deep hashing. Previous methods usually mitigate this problem by binary approximation, substituting binary codes for real-values via activation functions or regularizations. However, such approximation leads to uncertainty between real-values and binary ones, degrading retrieval performance. In this paper, we propose a novel Deep Momentum Uncertainty Hashing (DMUH). It explicitly estimates the uncertainty during training and leverages the uncertainty information to guide the approximation process. Specifically, we model bit-level uncertainty via measuring the discrepancy between the output of a hashing network and that of a momentum-updated network. The discrepancy of each bit indicates the uncertainty of the hashing network to the approximate output of that bit. Meanwhile, the mean discrepancy of all bits in a hashing code can be regarded as image-level uncertainty. It embodies the uncertainty of the hashing network to the corresponding input image. The hashing bit and the image with higher uncertainty are paid more attention during optimization. To the best of our knowledge, this is the first work to study the uncertainty in hashing bits. Extensive experiments are conducted on four datasets to verify the superiority of our method, including CIFAR-10, NUS-WIDE, MS-COCO, and a million-scale dataset Clothing1M. Our method achieves best performance on all datasets and surpasses existing state-of-the-arts by a large margin, especially on Clothing1M.


Collaborative Learning for Extremely Low Bit Asymmetric Hashing

Extremely low bit (e.g., 4-bit) hashing is in high demand for retrieval ...

Deep Reinforcement Learning with Label Embedding Reward for Supervised Image Hashing

Deep hashing has shown promising results in image retrieval and recognit...

Learning Decorrelated Hashing Codes for Multimodal Retrieval

In social networks, heterogeneous multimedia data correlate to each othe...

Hadamard Codebook Based Deep Hashing

As an approximate nearest neighbor search technique, hashing has been wi...

Rescuing Deep Hashing from Dead Bits Problem

Deep hashing methods have shown great retrieval accuracy and efficiency ...

Neurons Merging Layer: Towards Progressive Redundancy Reduction for Deep Supervised Hashing

Deep supervised hashing has become an active topic in web search and inf...

HHF: Hashing-guided Hinge Function for Deep Hashing Retrieval

Deep hashing has shown promising performance in large-scale image retrie...

Please sign up or login with your details

Forgot password? Click here to reset