Triplet Deep Hashing with Joint Supervised Loss for Fast Image Retrieval

Li, Mingyong; Wang, Hongya; Wang, Liangliang; Yang, Kaixiang; Xiao, Yingyuan

doi:10.1109/ictai.2019.00090

Cited by 3 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5) Universality on different hashing models: We argue that our proposed attack and defense algorithms are generic to the most popular hashing models with different backbones. To verify this point, we carry out non-targeted attacks (HAG and SDHA) on other hashing methods, including DPSH [4], HashNet [5] and CSQ [7]. The results are summarized in Table VIII.…”

Section: ) Analysis On Hyper-parametersmentioning

confidence: 99%

Deep Semantic-Alignment Hashing for Unsupervised Cross-Modal Retrieval

Yang

Zhang

et al. 2020

Proceedings of the 2020 International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

Section: ) Analysis On Hyper-parametersmentioning

confidence: 99%

Deep Semantic-Alignment Hashing for Unsupervised Cross-Modal Retrieval

Yang

Zhang

et al. 2020

Proceedings of the 2020 International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

“…(Semi-)Supervised (KSH [33], SDH [34]) utilize labeled information to improve binary codes. Recently, inspired by powerful deep networks, some deep hashing methods (CNNH [35], DPSH [36], SSGAH [37], ABML [38], ) have been proposed and achieve much better performance. They usually utilize a CNN to extract meaningful features, formulate the hashing function as a fully-connected layer with tanh/sigmoid activation function, and quantize features by signature function.…”

Section: Hashing Algorithmmentioning

confidence: 99%

“…( 2) is discrete and Hamming distance in Eq. ( 2) is not differentiable, a natural relaxation [36] is utilised in Eq. ( 5) by replacing sgn with tanh and changing the Hamming distance to the inner-product distance.…”

Section: Code Pyramidmentioning

confidence: 99%

Faster Person Re-Identification: One-Shot-Filter and Coarse-to-Fine Search

Wang,

Huang,

Gong

et al. 2024

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Fast person re-identification (ReID) aims to search person images quickly and accurately. The main idea of recent fast ReID methods is the hashing algorithm, which learns compact binary codes and performs fast Hamming distance and counting sort. However, a very long code is needed for high accuracy (e.g. 2048), which compromises search speed. In this work, we introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine (CtF) hashing code search strategy, which complementarily uses short and long codes, achieving both faster speed and better accuracy. It uses shorter codes to coarsely rank broad matching similarities and longer codes to refine only a few top candidates for more accurate instance ReID. Specifically, we design an All-in-One (AiO) module together with a Distance Threshold Optimization (DTO) algorithm. In AiO, we simultaneously learn and enhance multiple codes of different lengths in a single model. It learns multiple codes in a pyramid structure, and encourage shorter codes to mimic longer codes by self-distillation. DTO solves a complex threshold search problem by a simple optimization process, and the balance between accuracy and speed is easily controlled by a single parameter. It formulates the optimization target as a F β score that can be optimised by Gaussian cumulative distribution functions. Besides, we find even short code (e.g. 32) still takes a long time under large-scale gallery due to the O(n) time complexity. To solve the problem, we propose a gallery-size-free latent-attributes-based One-Shot-Filter (OSF) strategy, that is always O(1) time complexity, to quickly filter major easy negative gallery images, Specifically, we design a Latent-Attribute-Learning (LAL) module supervised a Single-Direction-Metric (SDM) Loss. LAL is derived from principal component analysis (PCA) that keeps largest variance using shortest feature vector, meanwhile enabling batch and end-to-end learning. Every logit of a feature vector represents a meaningful attribute. SDM is carefully designed for fine-grained attribute supervision, outperforming common metrics such as Euclidean and Cosine metrics. Experimental results on 2 datasets show that CtF+OSF is not only 2% more accurate but also 5× faster than contemporary hashing ReID methods. Compared with non-hashing ReID methods, CtF is 50× faster with comparable accuracy. OSF further speeds CtF by 2× again and upto 10× in total with almost no accuracy drop.

show abstract

“…As the first deep hashing algorithm, CNNH [3] consists of two independent stages, i.e., designing approximate hash codes of training data and learning feature representation through DNN. Recent hashing methods [4], [5], [7]- [12] focused on the design of end-to-end strategies and loss functions to improve the efficacy of hashing learning. For example, DPSH [4] integrated image representation and hash coding in a unified framework and adopted a pairwise loss to preserve the semantic similarity between data objects.…”

Section: Related Work a Deep Hashing-based Retrievalmentioning

confidence: 99%

“…Recent hashing methods [4], [5], [7]- [12] focused on the design of end-to-end strategies and loss functions to improve the efficacy of hashing learning. For example, DPSH [4] integrated image representation and hash coding in a unified framework and adopted a pairwise loss to preserve the semantic similarity between data objects. HashNet [5] proposed a continuous scale strategy to tackle the optimization problem in discrete Hamming space, and alleviated the data imbalance by a weighted pairwise loss.…”

Section: Related Work a Deep Hashing-based Retrievalmentioning

confidence: 99%

Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval

Zhang

Wang

et al. 2023

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Deep hashing has been intensively studied and successfully applied in large-scale image retrieval systems due to its efficiency and effectiveness. Recent studies have recognized that the existence of adversarial examples poses a security threat to deep hashing models, that is, adversarial vulnerability. Notably, it is challenging to efficiently distill reliable semantic representatives for deep hashing to guide adversarial learning, and thereby it hinders the enhancement of adversarial robustness of deep hashing-based retrieval models. Moreover, current researches on adversarial training for deep hashing are hard to be formalized into a unified minimax structure. In this paper, we explore Semantic-Aware Adversarial Training (SAAT) for improving the adversarial robustness of deep hashing models. Specifically, we conceive a discriminative mainstay features learning (DMFL) scheme to construct semantic representatives for guiding adversarial learning in deep hashing. Particularly, our DMFL with the strict theoretical guarantee is adaptively optimized in a discriminative learning manner, where both discriminative and semantic properties are jointly considered. Moreover, adversarial examples are fabricated by maximizing the Hamming distance between the hash codes of adversarial samples and mainstay features, the efficacy of which is validated in the adversarial attack trials. Further, we, for the first time, formulate the formalized adversarial training of deep hashing into a unified minimax optimization under the guidance of the generated mainstay codes. Extensive experiments on benchmark datasets show superb attack performance against the state-of-theart algorithms, meanwhile, the proposed adversarial training can effectively eliminate adversarial perturbations for trustworthy deep hashing-based retrieval.

show abstract

Triplet Deep Hashing with Joint Supervised Loss for Fast Image Retrieval

Cited by 3 publications

References 16 publications

Deep Semantic-Alignment Hashing for Unsupervised Cross-Modal Retrieval

Deep Semantic-Alignment Hashing for Unsupervised Cross-Modal Retrieval

Faster Person Re-Identification: One-Shot-Filter and Coarse-to-Fine Search

Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval

Contact Info

Product

Resources

About