Angular Deep Supervised Vector Quantization for Image Retrieval
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 1638-1649 |
Journal / Publication | IEEE Transactions on Neural Networks and Learning Systems |
Volume | 33 |
Issue number | 4 |
Online published | 23 Dec 2020 |
Publication status | Published - Apr 2022 |
Link(s)
Abstract
Most of the deep quantization methods adopt unsupervised approaches, and the quantization process usually occurs in the Euclidean space on top of the deep feature and its approximate value. When this approach is applied to the retrieval tasks, since the internal product space of the retrieval process is different from the Euclidean space of quantization, minimizing the quantization error (QE) does not necessarily lead to a good performance on the maximum inner product search (MIPS). To solve these problems, we treat Softmax classification as vector quantization (VQ) with angular decision boundaries and propose angular deep supervised VQ (ADSVQ) for image retrieval. Our approach can simultaneously learn the discriminative feature representation and the updatable codebook, both lying on a hypersphere. To reduce the QE between centroids and deep features, two regularization terms are proposed as supervision signals to encourage the intra-class compactness and inter-class balance, respectively. ADSVQ explicitly reformulates the asymmetric distance computation in MIPS to transform the image retrieval process into a two-stage classification process. Moreover, we discuss the extension of multiple-label cases from the perspective of quantization with binary classification. Extensive experiments demonstrate that the proposed ADSVQ has excellent performance on four well-known image data sets when compared with the state-of-the-art hashing methods.
Research Area(s)
- Deep learning, image retrieval, nearest neighbor search, neural networks, vector quantization (VQ)
Citation Format(s)
Angular Deep Supervised Vector Quantization for Image Retrieval. / Zhou, Chang; Po, Lai Man; Ou, Weifeng.
In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 33, No. 4, 04.2022, p. 1638-1649.
In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 33, No. 4, 04.2022, p. 1638-1649.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review