DSSN: dual shallow Siamese network for fashion image retrieval

Islam, Sk Maidul; Joardar, Subhankar; Sekh, Arif Ahmed

doi:10.1007/s11042-022-14204-0

Cited by 9 publications

(1 citation statement)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Islam et al proposed a doubly shallow concatenated network (DSSN) [30], a model with two identical concatenated networks, but with the same image in different ways as the output.…”

Section: Related Workmentioning

confidence: 99%

Multi-scale Atrous convolution and depth hash model

Liao

Lin

Yao

et al. 2023

Preprint

View full text Add to dashboard Cite

How to propose an image retrieval algorithm with adaptable model and wide range of applications for large-scale datasets has become a critical technical problem in current image retrieval. This paper proposes an incremental image retrieval algorithm based on Atrous convolution and deep hashing with an image retrieval system as the research object. The algorithm contains two important parts: the hash function learning part and the incremental hash code mapping part. Firstly, a module is designed called feature-aware to obtain multi-scale global context-aware information. It also keeps the scale and shape of the final extracted deep features invariant. Then, a new incremental hash loss function is designed to maintain the similarity between the query image and the dataset image. The experimental results show that the algorithm model can perform well in incremental image retrieval. It is shown that the algorithm can solve the current problem of low retrieval efficiency and high cost due to retraining models caused by the dramatic increase in the number of images in the image retrieval field.

show abstract

“…Islam et al proposed a doubly shallow concatenated network (DSSN) [30], a model with two identical concatenated networks, but with the same image in different ways as the output.…”

Section: Related Workmentioning

confidence: 99%