Abstract | ||
---|---|---|
As hashing becomes an increasingly appealing technique for large-scale image retrieval, multi-label hashing is also attracting more attention for the ability to exploit multi-level semantic contents. In this paper, we propose a novel deep hashing method for scalable multi-label image search. Unlike existing approaches with conventional objectives such as contrast and triplet losses, we employ a rank list, rather than pairs or triplets, to provide sufficient global supervision information for all the samples. Specifically, a new rank-consistency objective is applied to align the similarity orders from two spaces, the original space and the hamming space. A powerful loss function is designed to penalize the samples whose semantic similarity and hamming distance are mismatched in two spaces. Besides, a multi-label softmax cross-entropy loss is presented to enhance the discriminative power with a concise formulation of the derivative function. In order to manipulate the neighborhood structure of the samples with different labels, we design a multi-label clustering loss to cluster the hashing vectors of the samples with the same labels by reducing the distances between the samples and their multiple corresponding class centers. The state-of-the-art experimental results achieved on three public multi-label datasets, MIRFLICKR-25K, IAPRTC12 and NUS-WIDE, demonstrate the effectiveness of the proposed method. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/TMM.2020.3034534 | IEEE TRANSACTIONS ON MULTIMEDIA |
Keywords | DocType | Volume |
Image retrieval, Semantics, Binary codes, Task analysis, Neural networks, Quantization (signal), Training, Hashing, multi-label, image retrieval, rank-consistency, deep neural network | Journal | 23 |
Issue | ISSN | Citations |
1 | 1520-9210 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |