Research Article
[Retracted] Deep Unsupervised Hashing for Large-Scale Cross-Modal Retrieval Using Knowledge Distillation Model
Table 3
The MAP@50 results of two retrieval tasks on NUS-WIDE with various code lengths.
| Methods | Image-query-text | Text-query-image | 16 | 32 | 64 | 128 | 16 | 32 | 64 | 128 |
| CVH [7] | 0.372 | 0.362 | 0.406 | 0.390 | 0.401 | 0.384 | 0.442 | 0.432 | IMH [11] | 0.470 | 0.473 | 0.476 | 0.459 | 0.478 | 0.483 | 0.472 | 0.462 | CMFH [24] | 0.455 | 0.459 | 0.465 | 0.467 | 0.529 | 0.577 | 0.614 | 0.645 | LSSH [26] | 0.481 | 0.489 | 0.507 | 0.507 | 0.455 | 0.459 | 0.416 | 0.473 | DBRC [31] | 0.424 | 0.459 | 0.447 | 0.447 | 0.455 | 0.459 | 0.416 | 0.473 | UDCMH [28] | 0.511 | 0.519 | 0.524 | 0.558 | 0.637 | 0.653 | 0.695 | 0.716 | DJSRH [29] | 0.724 | 0.773 | 0.798 | 0.817 | 0.712 | 0.744 | 0.771 | 0.789 | JDSH [27] | 0.736 | 0.793 | 0.832 | 0.835 | 0.721 | 0.785 | 0.794 | 0.804 | Ours | 0.764 | 0.809 | 0.837 | 0.836 | 0.759 | 0.796 | 0.808 | 0.819 |
|
|