DeepMark: One-Shot Clothing Detection

Sidnev, Alexey; Trushkov, Alexey; Kazakov, Maxim; Korolev, I. A.; Сорокин, В. М.

doi:10.1109/iccvw.2019.00399

Cited by 16 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sidnev et al [24] presented a single-stage multiple-clothing detector based on CenterNet for clothing detection and landmark estimation. CenterNet [25] performs detection by estimating only one center point for each object.…”

Section: Deepmarkmentioning

confidence: 99%

Multiple-Clothing Detection and Fashion Landmark Estimation Using a Single-Stage Detector

et al. 2021

View full text Add to dashboard Cite

Fashion image analysis has attracted significant research attention owing to the availability of large-scale fashion datasets with rich annotations. However, existing deep learning models for fashion datasets often have high computational requirements. In this study, we propose a new model suitable for low-power devices. The proposed network is a one-stage detector that rapidly detects multiple cloths and landmarks in fashion images. The network is designed as a modification of the EfficientDet originally proposed by Google Brain. The proposed network simultaneously trains the core input features with different resolutions and applies compound scaling to the backbone feature network. The bounding box/class/landmark prediction networks maintain the balance between the speed and accuracy. Moreover, a low number of parameters and low computational cost make it efficient. Without image preprocessing, we achieved 0.686 mean average precision (mAP) in the bounding box detection and 0.450 mAP in the landmark estimation on the DeepFashion2 validation dataset with an inference time of 42 ms. We obtained optimal results in extensive experiments with loss functions and optimizers. Furthermore, the proposed method has the advantage of operating in low-power devices.

show abstract

Section: Deepmarkmentioning

confidence: 99%

Multiple-Clothing Detection and Fashion Landmark Estimation Using a Single-Stage Detector

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Although clothing detection is the foundation of fashion image understanding, little research work is devoted to it specifically. For example, the Match R-CNN (Ge et al 2019) is adapted from the region-proposal based detector Mask R-CNN (He et al 2017) with extra branches for fashion landmark estimation and fashion retrieval; the DeepMark (Sidnev et al 2019) model is a fashion-version of the anchor-free detector CenterNet (Zhou, Wang, and Krähenbühl 2019). In contrast, based on the essential properties of clothing, we design a new method that is guided by fashion landmarks to detect garments in particular.…”

Section: Fashion Detection and Landmark Detectionmentioning

confidence: 99%

“…In addition, we directly generate bounding boxes from these predicted keypoints rather than separately regressing them in another branch because the keypoints are real points on a garment, which should be easier to locate than the corner points of bounding box that do not actually exist. Different from previous methods (Ge et al 2019;Sidnev et al 2019), where a parallel-connection paradigm is employed, our method is built upon a series-connection strategy between keypoints estimation and clothing detection to make full use of keypoint cues.…”

Section: Introductionmentioning

confidence: 99%

KGDet: Keypoint-Guided Fashion Detection

Qian

Lian

Zhao

et al. 2021

AAAI

View full text Add to dashboard Cite

Locating and classifying clothes, usually referred to as clothing detection, is a fundamental task in fashion analysis. Motivated by the strong structural characteristics of clothes, we pursue a detection method enhanced by clothing keypoints, which is a compact and effective representation of structures. To incorporate the keypoint cues into clothing detection, we design a simple yet effective Keypoint-Guided clothing Detector, named KGDet. Such a detector can fully utilize information provided by keypoints with the following two aspects: i) integrating local features around keypoints to benefit both classification and regression; ii) generating accurate bounding boxes from keypoints. To effectively incorporate local features , two alternative modules are proposed. One is a multi-column keypoint-encoding-based feature aggregation module; the other is a keypoint-selection-based feature aggregation module. With either of the above modules as a bridge, a cascade strategy is introduced to refine detection performance progressively. Thanks to the keypoints, our KGDet obtains superior performance on the DeepFashion2 dataset and the FLD dataset with high efficiency.

show abstract

“…With the popularization of various applications on the Internet and the development of online fashion clothing shopping, the amount of multimedia data has increased dramatically, which led to a huge demand for automatic and accurate recognition and extraction from abundant image information. To satisfy these demands, various tasks have emerged in the clothes domain, such as clothing retrieval, 1–3 clothing detection, 4 person re‐identification, 5 and semantic segmentation of clothing 6,7 . The description of the clothing can be achieved by attribute information 8–13 .…”

Section: Introductionmentioning

confidence: 99%

Clothing attribute recognition via a holistic relation network

Zhou

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

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.

show abstract

DeepMark: One-Shot Clothing Detection

Cited by 16 publications

References 28 publications

Multiple-Clothing Detection and Fashion Landmark Estimation Using a Single-Stage Detector

Multiple-Clothing Detection and Fashion Landmark Estimation Using a Single-Stage Detector

KGDet: Keypoint-Guided Fashion Detection

Clothing attribute recognition via a holistic relation network

Contact Info

Product

Resources

About