Understanding Fashion Trends from Street Photos via Neighbor-Constrained Embedding Learning

Gu, Xiaoling; Wong, Yongkang; Peng, Pai; Shou, Lidan; Chen, Gang; Kankanhalli, Mohan

doi:10.1145/3123266.3123441

Cited by 34 publications

(33 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the related machine learning methods in the fashion field, three data sets, Fashionista [26], Fashion 144k [27], and SFS [28] are widely used. The detailed information…”

Section: Experiments and Evaluation A Experiments Setting 1) Data mentioning

confidence: 99%

A Multi-Task Learning Model for Better Representation of Clothing Images

2019

View full text Add to dashboard Cite

Clothing images vary in style and everyone has a different understanding of style. Even with the current popular deep learning methods, it is difficult to accurately classify style labels. A style representation learning model based on the deep neural networks called StyleNet is proposed in this paper. We adopt a multi-task learning framework to build the model and make full use of various types of label information to represent the clothing images in a finer-grained manner. Due to the semantic abstraction of image labels in the current fashion field, using a simple migration learning method cannot fully meet the requirements of clothing image classification. An objective function optimization method is put forward by combining the distance confusion loss and the traditional cross entropy loss to improve the accuracy of StyleNet further. The experimental results show that by applying the multi-task representation learning framework, StyleNet can achieve a better classification accuracy, the optimized loss function can also bring performance improvement for deep learning models, and the classification effect of StyleNet becomes better as the size of the data set increases. In order to verify the robustness and effectiveness of the deep learning method in StyleNet, we also apply a Faster R-CNN module to pre-process the clothing images and use the result as the input of StyleNet. The classifier can only get a limited performance improvement, which is negligible compared with the methods proposed in this paper of increasing the depth of the neural network and optimizing the loss function.

show abstract

“…To evaluate the related machine learning methods in the fashion field, three data sets, Fashionista [26], Fashion 144k [27], and SFS [28] are widely used. The detailed information…”

Section: Experiments and Evaluation A Experiments Setting 1) Data mentioning

confidence: 99%

A Multi-Task Learning Model for Better Representation of Clothing Images

2019

View full text Add to dashboard Cite

show abstract

“…Recently, the huge amount of potential benefits of fashion industry have attracted many researchers' attention from the computer vision to the multimedia research communities. Existing efforts mainly focus on clothing retrieval [11,20,21], fashion trending prediction [5], fashionability prediction [19] and compatibility modeling [6]. For example, Liu et al [20] presented a latent Support Vector Machine [4] model for both occasionoriented outfit and item recommendation based on a dataset of wild street photos, constructed by manual annotations.…”

Section: Related Work 21 Fashion Analysesmentioning

confidence: 99%

“…The superscripts t and b refer to top and bottom. s : R → R is a non-linear function applied element wise 5 . We treat the output of the Kth layer as the latent representations for tops and bottoms, i.e.,…”

Section: Data-driven Compatibility Modelingmentioning

confidence: 99%

“…Towards this end, to accurately model the implicit relations between the tops and bottoms, we naturally adopt the BPR framework, which has proven to be effective in the implicit preference modeling [9]. In particular, we assume that 5 In this work, we use the sigmoid function s(x ) = 1/(1 + e −x ). bottoms from the positive set B + i are more compatible to top t i than those non-composed neutral bottoms.…”

Section: Data-driven Compatibility Modelingmentioning

confidence: 99%

“…Figure 5 shows the changes of the objective function in Eqn. (5) and the training AUC with one iteration of our algorithm. As we can see, both values first change rapidly in a few epochs and then go steady finally, which well demonstrates the convergence of our model.…”

Section: Experimental Settingsmentioning

confidence: 99%

See 2 more Smart Citations

Neural Compatibility Modeling with Attentive Knowledge Distillation

Song¹,

Feng

Han³

et al. 2018

The 41st International ACM SIGIR Conference on Research &Amp; Development in Information Retrieval

112

View full text Add to dashboard Cite

Recently, the booming fashion sector and its huge potential benefits have attracted tremendous attention from many research communities. In particular, increasing research efforts have been dedicated to the complementary clothing matching as matching clothes to make a suitable outfit has become a daily headache for many people, especially those who do not have the sense of aesthetics. Thanks to the remarkable success of neural networks in various applications such as image classification and speech recognition, the researchers are enabled to adopt the data-driven learning methods to analyze fashion items. Nevertheless, existing studies overlook the rich valuable knowledge (rules) accumulated in fashion domain, especially the rules regarding clothing matching. Towards this end, in this work, we shed light on complementary clothing matching by integrating the advanced deep neural networks and the rich fashion domain knowledge. Considering that the rules can be fuzzy and different rules may have different confidence levels to different samples, we present a neural compatibility modeling scheme with attentive knowledge distillation based on the teacherstudent network scheme. Extensive experiments on the real-world dataset show the superiority of our model over several state-ofthe-art baselines. Based upon the comparisons, we observe certain fashion insights that add value to the fashion matching study. As a byproduct, we released the codes, and involved parameters to benefit other researchers.

show abstract