Geospatial big data: Survey and challenges

J Wu, W Gan, HC Chao… - IEEE Journal of Selected …, 2024‏ - ieeexplore.ieee.org
In recent years, geospatial big data (GBD) has obtained attention across various disciplines,
categorized into big Earth observation data and big human behavior data. Identifying …

On the robustness of large multimodal models against image adversarial attacks

X Cui, A Aparcedo, YK Jang… - Proceedings of the IEEE …, 2024‏ - openaccess.thecvf.com
Recent advances in instruction tuning have led to the development of State-of-the-Art Large
Multimodal Models (LMMs). Given the novelty of these models the impact of visual …

Computation-efficient deep learning for computer vision: A survey

Y Wang, Y Han, C Wang, S Song… - Cybernetics and …, 2024‏ - ieeexplore.ieee.org
Over the past decade, deep learning models have exhibited considerable advancements,
reaching or even exceeding human-level performance in a range of visual perception tasks …

Ags: Affordable and generalizable substitute training for transferable adversarial attack

R Wang, Y Guo, Y Wang - Proceedings of the AAAI Conference on …, 2024‏ - ojs.aaai.org
In practical black-box attack scenarios, most of the existing transfer-based attacks employ
pretrained models (eg ResNet50) as the substitute models. Unfortunately, these substitute …

Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing

L He, Z Huang, J Liu, E Chen, F Wang, J Sha… - Proceedings of the …, 2024‏ - dl.acm.org
Unsupervised semantic hashing has emerged as an indispensable technique for fast image
search, which aims to convert images into binary hash codes without relying on labels …

Discrepancy and structure-based contrast for test-time adaptive retrieval

Z Ma, Y Li, Y Luo, X Luo, J Li, C Chen… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Domain adaptive hashing has received increasing attention since it is capable of enhancing
the performance of retrieval if the target domain for testing meets domain shift. However …

Deep debiased contrastive hashing

R Wei, Y Liu, J Song, Y **e, K Zhou - Pattern recognition, 2023‏ - Elsevier
Hashing has achieved great success in multimedia retrieval due to its high computing
efficiency and low storage cost. Recently, contrastive-learning-based hashing methods have …

One-bit deep hashing: Towards resource-efficient hashing model with binary neural network

L He, Z Huang, C Liu, R Li, R Wu, Q Liu… - Proceedings of the 32nd …, 2024‏ - dl.acm.org
Deep Hashing (DH) has emerged as an indispensable technique for fast image search in
recent years. To deploy DH on resource-limited devices, the Binary Neural Network (BNN) …

From data to optimization: Data-free deep incremental hashing with data disambiguation and adaptive proxies

Q Su, D Wu, C Wu, B Li, W Wang - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Deep incremental hashing methods require a large number of original training samples to
preserve old knowledge. However, the old training samples are not always available. This …

[HTML][HTML] Performance evaluation of attention-deep hashing based medical image retrieval in brain MRI datasets

Y Chen, Z He, MA Ashraf, X Chen, Y Liu, X Ding… - Journal of Radiation …, 2024‏ - Elsevier
Background Brain MRI images pose significant challenges due to their complexity and
voluminous data, which often hinder the accuracy of traditional image retrieval methods. In …