Clothing Dataset Research Articles

P D N: A Priori Dictionary Network for Fashion Parsing

The task of fashion parsing aims to assign pixel-level labels to clothing targets; thereby, parsing models are required to have good contextual recognition ability. However, the shapes of clothing components are complex, and the types are difficult to distinguish. Recent solutions focus on improving datasets and supplying abundant priori information, but the utilization of features by more efficient methods is rarely explored. In this paper, we propose a multi-scale fashion parsing model called the Priori Dictionary Network (PDN), which includes a priori attention module and a multi-scale backbone. The priori attention module extracts high dimensional features from our designed clothing average template as a priori information dictionary (priori dictionary, PD), and the PD is utilized to activate the feature maps of a CNN from a multi-scale attention mechanism. The backbone is derived from classical models, and five side paths are designed to leverage the richer features of local and global contextual representations. To measure the performance of our method, we evaluated the model on four public datasets, the CFPD, UTFR-SBD3, ModaNet and LIP, and the experimental results show that our model stands out from other State of the Art in all four datasets. This method can assist with the labeling problem of clothing datasets.

Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network

Recommendations for clothing design styles provide a tailored and efficient buying experience, decreasing consumers' decision fatigue and boosting interest. There are a number of obstacles to implementing clothing design style recommendations, including the requirement for diverse and accurate data to train efficient algorithms, the possibility of biases in recommendation systems, the complexity of comprehending subtle customer preferences, and the ever-changing nature of fashion trends. To overcome this complication, Clothing Design Style Recommendation Using Optimized Semantic-Preserved Generative Adversarial Network (ICMA-SPGAN-SFOA-CD) are proposed. Initially, the images collected from the clothing dataset are given as input. Afterward, the data are fed to pre-processing. In pre-processing, Reverse Image Filter (RIF) is used for redundant of data and noise removal. The pre-processing output is fed to Pyramidal Convolution Shuffle Attention Neural Network (PCSANN) for clothing design style recommendation. The recommended clothing design style was given for classification using Semantic-Preserved Generative Adversarial Network (SPGAN) optimized with Sheep Flock Optimization Algorithm (SFOA)for classifying clothing design style as Basic clothing, Looseness Season for clothing, Collar type, Colour and Advanced clothing . MATLAB is used to implement the proposed ICMA-SPGAN-SFOA-CD method. The performance of the proposed ICMA-SPGAN-SFOA-CD approach attains 25%, 21.5%, and 22.5% high precision,25.3%, 27.5%, and 21.8% high recall and 27.6%, 24.8%, and 23.2% high F1-Scorecompared with existing methods such as RCNN Framework Using L-Softmax Loss (CAR-RCNN-LSL) ,Clothing Attribute Recognition Based on Clothing fashion style recognition with design issue graph (CFSR-DCNN-DIG), Personalized Smart Clothing Design Based on Multimodal Visual Data Detection (PSCD-DNN-MVDD) models respectively.

YOLOv8-MPEB small target detection algorithm based on UAV images

Target detection in Unmanned Aerial Vehicle (UAV) aerial images has gained significance within UAV application scenarios. However, UAV aerial images present challenges, including large-scale changes, small target sizes, complex scenes, and variable external factors, resulting in missed or false detections. This study proposes an algorithm for small target detection in UAV images based on an enhanced YOLOv8 model termed YOLOv8-MPEB. Firstly, the Cross Stage Partial Darknet53 (CSPDarknet53) backbone network is substituted with the lightweight MobileNetV3 backbone network, consequently reducing model parameters and computational complexity, while also enhancing inference speed. Secondly, a dedicated small target detection layer is intricately designed to optimize feature extraction for multi-scale targets. Thirdly, the integration of the Efficient Multi-Scale Attention (EMA) mechanism within the Convolution to Feature (C2f) module aims to enhance the extraction of vital features and suppress superfluous ones. Lastly, the utilization of a bidirectional feature pyramid network (BiFPN) in the Neck segment serves to ameliorate detection errors stemming from scale variations and complex scenes, thereby augmenting model generalization. The study provides a thorough examination by conducting ablation experiments and comparing the results with alternative algorithms to substantiate the enhanced effectiveness of the proposed algorithm, with a particular focus on detection performance. The experimental outcomes illustrate that with a parameter count of 7.39 M and a model size of 14.5 MB, the algorithm attains a mean Average Precision (mAP) of 91.9 % on the custom-made helmet and reflective clothing dataset. In comparison to standard YOLOv8 models, this algorithm elevates average accuracy by 2.2 percentage points, reduces model parameters by 34 %, and diminishes model size by 32 %. It outperforms other prevalent detection algorithms in terms of accuracy and speed.

Clothing Recommendation System Using the K-Nearest Neighbor Method

The world of fashion and the way we interact with it has been transformed by advances in information and communication technology. Clothing recommendation applications have become increasingly common, helping people choose clothes that suit their style and preferences. This study suggests using the KNN Method as a basis for building a more intelligent and personalized clothing recommendation system. To address the growing need for accurate clothing recommendations that match users' preferences, The goal of this research is to create a clothing recommendation system that can help users choose more appropriately because advances in technology have made it possible to gather and examine user data more thoroughly. In this study, the clothing recommendation system was implemented using the KNN Method. We ran simulations by setting the clothing dataset's parameter K value from 3 to 11. The simulation results show that the system's performance reaches its peak at parameter value K=8. We measured the system's accuracy, precision, and recall at this K value in order to assess its performance. The results show that the clothing recommendation system uses the KNN Method. A clothing recommendation system based on the KNN Method with the parameter K=8 has proven successful in classifying clothes with an accuracy of 83,67%.

Research on image recognition of ethnic minority clothing based on improved vision transformer

Due to the complex ornamentation and special composition of ethnic minority costumes, the performance of current costume image recognition algorithms is limited.Models based on convolutional neural networks can extract deep semantic features from clothing images, and perform better in datasets with more images, but ignore the large-scale features of images along the dimensional direction. Therefore, we propose an improved model based on Vision Transformer, which extracts the features of the image along the height and width directions through asymmetric convolution, and then inputs them into the Transformer encoder for serialization and encoding, and uses its output to get the recognition result. Using the accuracy as the evaluation index on the minority clothing dataset, the results show that the method we proposed performs better than ResNet34, and is 1.2% higher than the classic Vision Transformer.

A contrast-composition-distraction framework to understand product photo background's impact on consumer interest in E-commerce

In e-commerce, product photos are a major component of product presentations that aid consumers' understanding of products. In this study, we investigate the impact of the background of product photos on consumers' interest. Drawing upon the attention theories of visual perception, we propose a contrast-composition-distraction framework to understand the product photo background's impact. We conduct an empirical study using a clothing dataset collected from a major fashion product website in China. After differentiating photos' foreground and background and generating features using machine learning, we apply a hierarchical Bayesian model and find that consumers prefer clothing products to be shown on a darker and simpler background. The product should be located in the center of the photo with a slight horizontal offset. It is preferable to use a blurred background and reduce the use of human model faces. These findings are of substantial theoretical and practical value to e-commerce.

YOLO-FL: A target detection algorithm for reflective clothing wearing inspection

In recent years, target detection has been widely used in specific dress detection, to reduce the probability of accidents in certain fields such as construction sites, traffic management, etc. However, the detection of professional dress, especially reflective clothing, is mainly relied on manual detection so far, with the disadvantages of low efficiency and high time consumption. To this end, we focus on reflective clothing and propose the YOLO-FL detection algorithm based on YOLOV4-tiny. Firstly, a new intersection and union ratio calculation method KIoU is proposed and introduced into the original K-means++ clustering method to avoid the influence brought by distance in the original K-means++ clustering method. Secondly, the SPPF module is introduced into the neck network to make the feature information of different scales fully integrated and obtain a richer feature representation. Finally, the label smoothing strategy is used to optimize the loss function of the network model to prevent the network from overfitting and to improve the generalization ability of the model to a certain extent. We tested on the self-made reflective clothing dataset, and the mAP and F1 values of the YOLO-FL algorithm were 91.14% and 0.85, respectively, which improved by 8.29% and 0.12, respectively, compared with the original algorithm. In addition, experiments on PASCAL VOC and MS-COCO datasets show that the accuracy of the YOLO-FL algorithm has significantly improved (+4.77% on the Pascal VOC benchmark and +2.49% on the MS-COCO benchmark), and has excellent migration generalization performance.

FFENet: frequency-spatial feature enhancement network for clothing classification.

Clothing analysis has garnered significant attention, and within this field, clothing classification plays a vital role as one of the fundamental technologies. Due to the inherent complexity of clothing scenes in real-world environments, the learning of clothing features in such complex scenes often encounters interference. Because clothing classification relies on the contour and texture information of clothing, clothing classification in real scenes may lead to poor classification results. Therefore, this paper proposes a clothing classification network based on frequency-spatial domain conversion. The proposed network combines frequency domain information with spatial information and does not compress channels. It aims to enhance the extraction of clothing features and improve the accuracy of clothing classification. In our work, (1) we combine the frequency domain information and spatial information to establish a clothing feature extraction clothing classification network without compressed feature map channels, (2) we use the frequency domain feature enhancement module to realize the preliminary extraction of clothing features, and (3) we introduce a clothing dataset in complex scenes (Clothing-8). Our network achieves a top-1 model accuracy of 93.4% on the Clothing-8 dataset and 94.62% on the Fashion-MNIST dataset. Additionally, it also achieves the best results in terms of top-3 and top-5 metrics on the DeepFashion dataset.

OMNet: Outfit Memory Net for clothing parsing

PurposeExisting clothing parsing methods make little use of dataset-level information. This paper aims to propose a novel clothing parsing method which utilizes higher-level outfit combinatorial consistency knowledge from the whole clothing dataset to improve the accuracy of segmenting clothing images.Design/methodology/approachIn this paper, the authors propose an Outfit Memory Net (OMNet) that augments original feature by aggregating dataset-level prior clothing combination information. Specifically, the authors design an Outfit Matrix (OM) to represent clothing combination information of single image and an Outfit Memory Module (OMM) to store the clothing combination information of all images in the training set, i.e. dataset-level clothing combination information. In addition, the authors propose a Multi-scale Aggregation Module (MAM) to aggregate the clothing combination information in a multi-scale manner to solve the problem of large variance in the scale of objects in the clothing images.FindingsExperiments on Colorful Fashion Parsing Dataset (CFPD) dataset show that the authors' method achieves 93.15% pixel accuracy (PA) and 51.24% mean of class-wise intersection over union (mIoU), which are satisfactory parsing results compared with existing methods such as PSPNet, DANet and DeepLabV3. Moreover, through comparing the segmentation accuracy of different methods for each category, MAM could effectively improve the segmentation of small objects.Originality/valueWith the rise of various online shopping platforms and the continuous development of deep learning technology, emerging applications such as clothing recommendation, matching, classification and virtual try-on system have emerged in the clothing field. Clothing parsing is the key technology to realize these applications. Therefore, improving the accuracy of clothing parsing is necessary.

Implementation of CNN and ANN for Fashion-MNIST-Dataset using Different Optimizers

Objectives: The paper presents application of convolution neural network and artificial neural network for image classification problem for clothing dataset along with their performance comparison against different optimizers. The major objective of this paper is to perform image classification on fashion-mnist clothing dataset images. Methods: The methods used here are, the traditional ANN and CNN. Here image classification is performed on Fashion-mnist, clothing dataset using CNN and ANN with different optimizers. The performance of the working of ANN and CNN in classifying images from fashion-mnist dataset is compared against different optimizers namely stochastic gradient Descent, Adagrad, RMS prop and Adam optimizer. Findings: The study found that CNN worked better than ANN yielding training accuracy of 95%, 93% and testing accuracy of 91%, 89% when used with Adam and RmsProp respectively. Novelty: The novelty of this work is to present a comparative study of image classification using CNN, ANN using different optimizers, since not many studies or research articles showed the performance comparison of traditional and convolution neural networks in image classification along with different optimizers. Since the real-world scenarios of today require enormous data to be processed, CNN can fit well to diversify applications since they highly reduce the number of parameters to be trained that speeds up the training process. Moreover, to be specific on image classification problems they require the best and most prominent features to be detected and uncovered; this can be achieved using CNN since it has the concept of convolution using filters at its Core. Hence, CNN is highly recommended for such image classification applications than the traditional artificial-neural-networks because of the aforementioned reasons. Keywords: ANN (Artificial NeuralNetworks); CNN (ConvolutionNeural Networks); Optimization; SGD (Stochastic Gradient Descent); RmsProp (Root mean Square propagation); Adam (Adaptive moment estimation); AdaGrad (Adaptive Gradient)

Enhanced Context Learning with Transformer for Human Parsing

Human parsing is a fine-grained human semantic segmentation task in the field of computer vision. Due to the challenges of occlusion, diverse poses and a similar appearance of different body parts and clothing, human parsing requires more attention to learn context information. Based on this observation, we enhance the learning of global and local information to obtain more accurate human parsing results. In this paper, we introduce a Global Transformer Module (GTM) via a self-attention mechanism to capture long-range dependencies for effectively extracting context information. Moreover, we design a Detailed Feature Enhancement (DFE) architecture to exploit spatial semantics for small targets. The low-level visual features from CNN intermediate layers are enhanced by using channel and spatial attention. In addition, we adopt an edge detection module to refine the prediction. We conducted extensive experiments on three datasets (i.e., LIP, ATR, and Fashion Clothing) to show the effectiveness of our method, which achieves 54.55% mIoU on the LIP dataset, 80.26% on the average F-1 score on the ATR dataset and 55.19% on the average F-1 score on the Fashion Clothing dataset.

Clothing attribute recognition via a holistic relation network

Clothing attribute prediction is a fundamental image classification task in the field of computer vision. Motivated by the human recognition system, we investigate the task relationship and spatial importance where people usually utilize these useful clues to assist in recognizing clothing attributes. In this paper, we propose a novel Holistic Relation Network (HRNet) for clothing attribute recognition, considering the fusion of multiple relations, including spatial and spatial relation via a spatial relation module, spatial and task relation via a task attention module, and task and task relation via a graph context reasoning module. Specifically, we first use the backbone network to extract features from the input image, two types of attention models followed will further learn the features, then the graph context reasoning module will be used to further enhance the features, and finally, a classifier exploited to classify the clothing attributes with the learned representation information. Without using manual image feature filtering methods, this paper aims to achieve clothing attribute recognition by deeply exploring the relationships among different clothing attribute recognition tasks. In this paper, we use double-branches of the attention model to model the relevance of spatial context information and learn more discriminative feature representations from multitask features for clothing attribute prediction. Derived from the prior knowledge learned from the two above-mentioned attention models, we further propose a graph-relation model constructing relationships among different clothing attribute tasks by integrating the spatial association relationships among multitask. The proposed HRNet only uses image-level annotation but it owns a good ability for obtaining distinguishing feature representations. We obtain state-of-the-art performance, which is demonstrated by extensive experiments on three mainstream benchmarks, for example, woman clothing data set, man clothing data set, and shop-domain clothing data set.

Relatable Clothing: Soft-Attention Mechanism for Detecting Worn/Unworn Objects

We have identified a need in visual relationship detection and biometrics related research for a dataset and model which focuses on person-clothing pairs. Previous to our Relatable Clothing dataset, there were no publicly available datasets usable for “worn” and “unworn” clothing detection. In this paper we propose a novel visual relationship model architecture for “worn” and “unworn” clothing detection that makes use of a soft attention mechanism for feature fusion between a conventional ResNet backbone and our novel person-clothing mask feature extraction architecture. The best proposed model achieves 98.62% accuracy, 99.50% precision, 98.31% recall, and 99.14% specificity on the Relatable Clothing dataset, outperforming our previous iterations. We release our models which can be found on the Relatable Clothing GitHub repository (https://github.com/th-truong/relatable_clothing) for future research and applications into detecting and analyzing person-clothing pairs.

Garment customization big data–processing and analysis in optimization design

In order to adapt to the expansion and transformation of the garment customization, big data is increasingly used in the online customization process. The aim of our research was to propose a method of tailoring clothing throughout the early stages of personal design and product development. This approach improves the understanding of garment fitting by analyzing individual preferences, and also helps designers capture user needs more quickly and deal with them more accurately. Our approach is built upon garment customization using unsupervised approach to learning visual compatibility from clothing data sets. For the garment definition, a competitive analysis was made to identify garment custom process. Then, training model was applied in personal customization environment while examining the links through machine learning module. Indeed, garment customization with big data provides new insights into garment customization, in terms of effectively optimizing the combination of mix-and-match clothing choices as well as generative learning of fashion design.

A Novel Clothing Attribute Representation Network-Based Self-Attention Mechanism

As highly increasing of on-line fashions retail industry, automatic recognition and representation of clothing items have huge potentials. With the help of deep learning methods, many clothing attribute representation models have been proposed. However, these models are mainly suitable for coarse-grained classification which are not suitable for clothing attribute representation. To address such a problem, in this article, we propose a novel network structure named SAC, which is a combination of CNNs and Self-attention mechanism and can represent clothing attributes more fine-grained. Besides, we use Grad-CAM to visualize which part of the clothing attributes is more concerned by customers. Finally, a new labeled clothing dataset is introduced in this article, which is expected to be helpful to the researchers who are working in fashion domains for image representation.

Task-Aware Attention Model for Clothing Attribute Prediction

Clothing attribute recognition, especially in unconstrained street images, is a challenging task for multimedia. Existing methods for multi-task clothing attribute prediction often ignore the relation between specific attributes and positions. However, the attribute response is always location-sensitive, i.e., different spatial locations have various contributions to attributes. Inspired by the locality of clothing attributes, in this paper, we introduce the attention mechanism to incorporate the impact of positions for clothing attribute prediction with only image-level annotations. However, the performance improvement is limited if we directly use the traditional spatial attention model for each task since it does not take the influence from other tasks into account. Instead, we propose a novel task-aware attention mechanism, which estimates the importance of each position across different tasks. We first evaluate a task attention network with an end-to-end multi-task clothing attribute learning architecture on the shop domain. And then, we employ curriculum learning strategy, which transfers the well-trained shop domain attribute knowledge to the street domain attribute prediction. Experiments are conducted on three clothing benchmarks, i.e., cross-domain clothing attribute dataset, woman clothing dataset, and man clothing dataset. The performance of attribute prediction demonstrates the superiority of the proposed task-aware attention mechanism over several state-of-the-art methods both in shop and street domains.

How to Wear Beautifully? Clothing Pair Recommendation

In this paper, we present a practical system to automatically suggest the most pairing clothing items, given the reference clothing (upper-body or low-body). This has been a challenge, due to clothes having a variety of categories. Clothing is one of the most informative cues for human appearance. In our daily life, people need to wear properly and beautifully to show their confidence, politeness and social status in various occasions. However, it is not easy to decide what to wear and how to coordinate their own clothes. To address this problem, we propose a recommendation approach that includes clothing region detection, clothing pair recommendation and distance fusion. Clothing region detection based on Faster R-CNN is used to detect clothing region. Clothing pair recommendation consists of a quadruple network architecture, where one dual network of the architecture adopts Siamese convolution neural network architecture. Training examples are pairs of upper-body and low-body clothing items that are either compatible or incompatible. The other dual network is used to learn clothing style features of the input image. This framework is designed to learn a feature transformation from the images of clothing items into two latent spaces, which we call them compatible space and style space respectively. After training the two dual networks, we use a distance fusion method to fuse the features extracted from the compatible and style dual networks. To acquire an optimized model and verify our proposed method, we expand an existing large clothing dataset WoG (Weather-to-Garment), and the resulted dataset is called “How to Wear Beautifully” (H2WB). Experiments on the H2WB dataset demonstrate that our approach is effective with clothing region detection and clothing pair recommendation as well as distance fusion.

Watch fashion shows to tell clothing attributes

Abstract In this paper, we propose a novel semi-supervised method to predict clothing attributes with the assistance of unlabeled data like fashion shows. To this end, a two-stage framework is built, i.e., the unsupervised triplet network pre-training stage that ensures frames in the same video having coherent representations while frames from different videos having larger feature distances, and a supervised clothing attribute prediction stage to estimate the value of attributes. Specifically, we first detect the clothes of frames in the collected 18,737 female fashion shows and 21,224 male fashion shows which contain no extra labels. Then a triplet neural network is constructed via embedding the temporal appearance consistency between frames in the same video and the representation gap in different videos. Finally, we transfer the triplet model parameters to multi-task clothing attribute prediction model, and fine-tune it with clothing images holding attribute labels. Extensive experiments demonstrate the advantages of the proposed method on two clothing datasets.

Deep net architectures for visual-based clothing image recognition on large database

In the Big Data era, there is a need for powerful visual-based analytics tools when pictures have replaced texts and become main contents on the Internet. Hence, in this study, we explore convolutional neural networks with a goal of resolving clothing style classification and retrieval tasks. To reduce training complexity, low-level and mid-level features were learned in the deep models on large-scale datasets and then transfer learning is incorporated by fine-tuning pre-trained models using the clothing dataset. However, a large amount of collected data needs huge computations for tuning parameters. Therefore, one architecture inspired from Adaboost is designed to use multiple deep nets that are trained with a sub-dataset. Thus, the training time can be accelerated if each net is computed in one client node in a distributed computing environment. Moreover, to increase system flexibility, two architectures with multiple deep nets with two outputs are proposed for binary-class classification. Therefore, when new classes are added, no additional computation is needed for all training data. In order to integrate output responses from multiple nets, classification rules are proposed as well. Experiments are performed to compare existing systems with hand-crafted features. According to the results, the proposed system can provide significant improvements on three public clothing datasets for style classifications, particularly on the large dataset with 80,000 images where an improvement of 18% in accuracy was recognized.

Clothing-to-words mapping using word separation method

With the development of E-commerce, clothing search on Internet emerges to be a valuable and challenging problem. Compared with the standard image retrieval approach, there are two main difficulties in clothing search. The first is the numerous clothing variation. Another is that people like to search the clothing, which have the same visual elements under the numerous variation. Motivated by Graph Cut method, an approach called word separation method is proposed to map the clothing visual elements to words, which can simultaneously take into account the image-to-image relationship, the image-to-word relationship and the word-to-word relationship. In our work, the meaningful words from web pages are represented by the graph nodes. The graph edges are weighted by the context of data set, which is from Internet. The experimental results on the clothing data set demonstrate the efficiency, effectiveness and robustness of our method.