Pairwise Teacher-Student Network for Semi-Supervised Hashing
By Shifeng Zhang, Jianmin Li. 2019
9 citations recorded by the source corpus.
Hashing method maps similar high-dimensional data to binary hashcodes with smaller hamming distance, and it has received broad attention due to its low storage cost and fast retrieval speed. Pairwise similarity is easily obtained and widely used for retrieval, and most supervised hashing algorithms are carefully designed for the pairwise supervisions. As labeling all data pairs is difficult, semi-supervised hashing is proposed which aims at learning efficient codes with limited labeled pairs and abundant unlabeled ones. Existing methods build graphs to capture the structure of dataset, but they are not working well for complex data as the graph is built based on the data representations and determining the representations of complex data is difficult. In this paper, we propose a novel teacher-student semi-supervised hashing framework in which the student is trained with the pairwise information produced by the teacher network. The network follows the smoothness assumption, which achieves consistent distances for similar data pairs so that the retrieval results are similar for neighborhood queries. Experiments on large-scale datasets show that the proposed method reaches impressive gain over the supervised baselines and is superior to state-of-the-art semi-supervised hashing methods.
Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Networks and Communications
In Computer Vision and Pattern Recognition
Citations in the corpus
- Incremental Object Detection via Meta-Learning (2020, neutral): “This has found success in semi-supervised learning [50], [51], [52] and domain adaptation [53], [54], [55], [56] settings.”
- Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks (2020, methodology): “e student via consistency cost. Interestingly, in [2], the teacher’s weights are updated using the earth moving average (EMA) of the student’s weights. Inspired by [2], Luo et al. [225], Zhang et al. [226], French et al. [227], Choi et al. [228], Cai et al. [229] and Xu et al. [230] all employ simil”
- A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, methodology): “A teacher-student based semi-supervised image retrieval [171] uses the pairwise information learnt by the teacher network as the guidance to train the student network.”