Research Article
[Retracted] Deep Unsupervised Hashing for Large-Scale Cross-Modal Retrieval Using Knowledge Distillation Model
Table 2
The MAP@50 results of two retrieval tasks on MIRFLICKR with various code lengths.
| Methods | Image-query-text | Text-query-image | 16 | 32 | 64 | 128 | 16 | 32 | 64 | 128 |
| CVH [7] | 0.606 | 0.599 | 0.596 | 0.598 | 0.591 | 0.583 | 0.576 | 0.576 | IMH [11] | 0.612 | 0.601 | 0.592 | 0.579 | 0.603 | 0.595 | 0.589 | 0.580 | CMFH [24] | 0.621 | 0.624 | 0.625 | 0.627 | 0.642 | 0.662 | 0.676 | 0.685 | LSSH [26] | 0.584 | 0.599 | 0.602 | 0.614 | 0.618 | 0.626 | 0.626 | 0.628 | DBRC [31] | 0.617 | 0.619 | 0.620 | 0.621 | 0.618 | 0.626 | 0.626 | 0.628 | UDCMH [28] | 0.689 | 0.698 | 0.714 | 0.717 | 0.692 | 0.704 | 0.718 | 0.733 | DJSRH [29] | 0.810 | 0.843 | 0.862 | 0.876 | 0.786 | 0.822 | 0.835 | 0.847 | JDSH [27] | 0.832 | 0.853 | 0.882 | 0.892 | 0.825 | 0.864 | 0.878 | 0.880 | Ours | 0.854 | 0.876 | 0.893 | 0.905 | 0.837 | 0.867 | 0.882 | 0.884 |
|
|