Survey on clothing image retrieval with cross-domain

Chen, Ning; Yang, Di; Menglu, Li

doi:10.1007/s40747-022-00750-5

Cited by 9 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

“…Firstly, though we employed combinations of local features (TSD, SI and LBP) and global features (BSP, SIFT and FIN3D), in practical online or offline clothing retrieval scenarios, such feature combinations may not be comprehensive enough to capture finegrained details within diverse clothing subcategories. In the future, it is worth considering contrastive learning methods (Ning et al, 2022) to obtain more comprehensive features for subcategories and incorporate them into the feature combination process to enhance the classification and retrieval performance of RGBD clothing images. Secondly, although our proposed MEDFS method can select more discriminative features under supervised category conditions, surpassing existing unsupervised methods, it is still susceptible to sample noise and outliers, especially for subcategories with nearly identical colors and textures.…”

Section: Limitationmentioning

confidence: 99%

See 1 more Smart Citation

Manifold embedded global and local discriminative features selection for single-shot multi-categories clothing recognition and retrieval

Huang

2023

IJICC

View full text Add to dashboard Cite

PurposeSingle-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.Design/methodology/approachTo address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.FindingsEmpirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.Originality/valueThis paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Limitationmentioning

confidence: 99%

Manifold embedded global and local discriminative features selection for single-shot multi-categories clothing recognition and retrieval

Huang

2023

IJICC

View full text Add to dashboard Cite

show abstract

“…The progress of retrieval not only depends on the feature extraction but also on the score and size of each extracted feature [9]. Usually, the problem with high dimension features is that it increases the number of parameters that helps to train well but is computationally expensive [11].…”

Section: Proposed Methodsmentioning

confidence: 99%

“…The motivation behind this research is to increase the training and test accuracy of the clothes retrieval process. The progress of retrieval not only depends on the feature extraction but also on the score of each extracted feature [9]. Initially, the features are extracted through the baseline AlexNet with a little bit of modification i.e., the ReLU layer is replaced with a self-regularized Mish activation function [10].…”

Section: Introductionmentioning

confidence: 99%

Clothes Retrieval Using M-AlexNet With Mish Function and Feature Selection Using Joint Shannon’s Entropy Pearson’s Correlation Coefficient

et al. 2022

View full text Add to dashboard Cite

The online retrieval of images related to clothes is a crucial task because finding the exact items like the query image from a large amount of data is extremely challenging. However, large variations in clothes images degrade the retrieval accuracy of visual searches. Another problem with retrieval accuracy is high dimensions of feature vectors obtained from pre-trained deep CNN models. This research is an effort to enhance the training and test accuracy of clothes retrieval by using two different means. Initially, features are extracted using the modified AlexNet (M-AlexNet) with little modification in which ReLU activation function is replaced with a self-regularized Mish activation function because of its non-monotonic nature. The M-AlexNet with Mish is trained on CIFAR-10 dataset using SoftMax classifier. Another contribution is to reduce the dimensions of feature vectors obtained from M-AlexNet. The dimensions of features are reduced by selecting the top k ranked features and removing some of the dissimilar features using the proposed Joint Shannon's Entropy Pearson Correlation Coefficient (JSE-PCC) technique to enhance the clothes retrieval performance. To calculate the efficacy of suggested methods, the comparison is performed with other deep CNN models such as baseline AlexNet, VGG-16, VGG-19, and ResNet50 on DeepFashion2, MVC, and the proposed Clothes Image Dataset (CID). Extensive experiments indicate that AlexNet with Mish attains 85.15%, 82.04%, and 83.65% accuracy on DeepFashion2, MVC, and 83.65% on CID datasets respectively. Hence, M-AlexNet and the proposed feature selection technique surpassed the results with a margin of 5.11% on DeepFashion2, 1.95% on MVC, and 3.51% CID datasets.

show abstract

“…Similarity retrieval is an important research topic in the field of fashion [5,6,8,16,19,35], especially for inshop clothes retrieval [2,19] and cross-domain fashion retrieval [13,15,22]. Currently, the mainstream approaches in fine-grained fashion retrieval aim to learn a general embedding space to compute the similarity among fashion items, and the triplet loss is always adopted to train the model [10,38].…”

Section: Introductionmentioning

confidence: 99%

Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval

Liu¹,

Yamasaki²

2023

Preprint

View full text Add to dashboard Cite

This paper proposes an attribute-guided multi-level attention network (AG-MLAN) to learn fine-grained fashion similarity. AG-MLAN is able to make a more accurate attribute positioning and capture more discriminative features under the guidance of the specified attribute. Specifically, the AG-MLAN contains two branches, branch 1 aims to force the model to recognize different attributes, while branch 2 aims to learn multiple attribute-specific embedding spaces for measuring the fine-grained similarity. We first improve the Convolutional Neural Network (CNN) backbone to extract hierarchical feature representations, then the extracted feature representations are passed into branch 1 for attribute classification and branch 2 for multi-level feature extraction. In branch 2, we first propose a multi-level attention module to extract a more discriminative representation under the guidance of a specific attribute. Then, we adopt a masked embedding module to learn attribute-aware embedding. Finally, the AG-MLAN is trained with a weighted loss of the classification loss in branch 1 and the triplet loss of the masked embedding features in branch 2 to further improve the accuracy in attribute location. Extensive experiments on the DeepFashion, FashionAI, and Zappos50k datasets show the effectiveness of AG-MLAN for fine-grained fashion similarity learning and its potential for attribute-guided retrieval tasks. The proposed AG-MLAN outperforms the state-of-the-art methods in the fine-grained fashion similarity retrieval task.

show abstract

Survey on clothing image retrieval with cross-domain

Cited by 9 publications

References 34 publications

Manifold embedded global and local discriminative features selection for single-shot multi-categories clothing recognition and retrieval

Manifold embedded global and local discriminative features selection for single-shot multi-categories clothing recognition and retrieval

Clothes Retrieval Using M-AlexNet With Mish Function and Feature Selection Using Joint Shannon’s Entropy Pearson’s Correlation Coefficient

Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval

Contact Info

Product

Resources

About