DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations

By Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, Xiaoou Tang. 2016

1,972 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Taming Transformers for High-Resolution Image Synthesis (2020, methodology): “4 shows that the same approach as for the previous experiments can be used to build a shape-conditional generative model on the DeepFashion [41] dataset.”
Recent advances in convolutional neural networks (2015, methodology): “ the estimated center point cp = ( P N p i z (i) p )=N p . Triplet loss and its variants have been widely used in various tasks, including re-identication [82], verication [81], and image retrieval [83]. 3.4.5. Kullback-Leibler Divergence Kullback-Leibler Divergence (KLD) is a non-symmetric measure ”
Large-Scale Long-Tailed Recognition in an Open World (2019, background): “Arising from long-tail distributions of natural data, it has been extensively studied [41, 61, 3, 30, 62, 34, 29, 49, 6].”
A Disentangling Invertible Interpretation Network for Explaining Latent Representations (2020, methodology): “The subsequent experiments use the following datasets: AnimalFaces [28], DeepFashion [29, 31], CelebA [30] MNIST [27], Cifar10 [25], and FashionMNIST [50].”
Fully-Adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification (2016, methodology): “We evaluate top-3 and top-5 classiﬁcation accuracy to directly compare with benchmark results in [23].”
DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images (2019, methodology): “(c) shows that categories in DeepFashion [14] have ambiguity.”
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback (2021, methodology): “In addition, we enlist real users to collect the high-quality, natural language annotations, rather than using fully or partially automated approaches to acquire large amounts of weak attribute labels [41, 38, 46] or synthetic conversational data [48].”
Training Vision Transformers for Image Retrieval (2021, neutral): “In-Shop (Liu et al., 2016) contains 72,712 images of clothing items belonging to 7,986 categories, 3,997 of which used for training.”
RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval (2020, methodology): “eval process that is end-to-end trainable with the conditional generative model. Image Retrieval. Image retrieval has been a classical vision problem with numerous applications such as product search [24,6,1], multimodal image retrieval [36,3], image geolocalization [7], event detection [13], among ”
Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs (2017, background): “For instance, in the fashion industry visual attributes are crucial for product recommendations [Liu et al., 2016, Veit et al., 2015].”
Cross-Domain Correspondence Learning for Exemplar-Based Image Translation (2020, background): “• Deepfashion [31] consists of 52,712 person images in fashion clothes.”
ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis (2020, methodology): “retrieval datasets: the Caltech-UCSD Birds dataset [29] (CUB200), the Stanford Cars dataset [15] (Cars196), the Stanford Online Products dataset [23] (Sop), and the In Shop Clothing Retrieval dataset [16] (InShop). The composition in terms of number of images and classes of each dataset is summarize”
Imbalanced Deep Learning by Minority Class Incremental Rectification (2018, methodology): “We adopted a test setting that is consistent with all the other experiments: (1) The standard multi-label classification setting without using the clothing landmark and category labels (used in [30]).”
Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy (2019, methodology): “We used DeepFashion [18] as ID and TinyImageNet-crop (TINc)/LSUN-crop (LSUNc) as OOD.”
Long-CLIP: Unlocking the Long-Text Capability of CLIP (2024, methodology): “Moreover, we also use a dataset collected from DeepFashion [15] which contains 200 images and 200 similar texts to evaluate the fine-grained ability.”
Deep Multimodality Model for Multi-task Multi-view Learning (2019, background): “• Deepfashion [15] : • WebKB : This is a textual data set, which consists of over 4000 web pages from 4 universities and includes 3 views, including the content of the web page, the title of the web page and the links within the web page.”
Deep Metric Learning with Hierarchical Triplet Loss (2018, methodology): “Extensive experiments are conducted on a number of benchmarks, including In-Shop Clothes Retrieval [15] and Caltech-UCSD Birds 200 [31] for image retrieval, and LFW [8] for face veriﬁcation.”