Creating Something From Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing

By Hengtong Hu, Lingxi Xie, Richang Hong, Qi Tian. 2020

135 citations recorded by the source corpus.

In recent years, cross-modal hashing (CMH) has attracted increasing attentions, mainly because its potential ability of mapping contents from different modalities, especially in vision and language, into the same space, so that it becomes efficient in cross-modal data retrieval. There are two main frameworks for CMH, differing from each other in whether semantic supervision is required. Compared to the unsupervised methods, the supervised methods often enjoy more accurate results, but require much heavier labors in data annotation. In this paper, we propose a novel approach that enables guiding a supervised method using outputs produced by an unsupervised method. Specifically, we make use of teacher-student optimization for propagating knowledge. Experiments are performed on two popular CMH benchmarks, i.e., the MIRFlickr and NUS-WIDE datasets. Our approach outperforms all existing unsupervised methods by a large margin.

Subfields: 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 Vision and Pattern Recognition

1. Dacheng Tao
2. Jianping Gou
3. S. Maybank
4. Baosheng Yu
5. Zhen-Duo Chen
6. Xin Luo
7. Xin-Shun Xu
8. Yongxin Wang

Citations in the corpus

• Knowledge Distillation: A Survey (2020, methodology): “Specifically, in (Chen et al., 2019a; Ye et al., 2020; Micaelli and Storkey, 2019; Yoo et al., 2019; Hu et al., 2020), the transfer data is generated by a GAN.”
• High-Dimensional Sparse Cross-Modal Hashing with Fine-Grained Similarity Embedding (2021, methodology): “Representative methods include Inter-Media Hashing (IMH) [43], Collective Matrix Factorization Hashing (CMFH) [9], Composite Correlation Quantization (CCQ) [32], Fusion Similarity Hashing (FSH) [29], Robust and Flexible Discrete Hashing (RFDH) [47], Collective Reconstructive Embedding (CRE) [16], Ro”