Min-Entropy Latent Model for Weakly Supervised Object Detection

Wan, Fang; Wei, Pengxu; Jiao, J. B.; Han, Zhenjun; Ye, Qixiang

doi:10.1109/cvpr.2018.00141

Cited by 207 publications

(120 citation statements)

References 29 publications

Supporting

Mentioning

117

Contrasting

Unclassified

Order By: Relevance

“…Typically, training the object detection models needs fully annotated data, while obtaining the annotations is very time‐consuming. Therefore, some researchers proposed several weakly supervised methods to address this issue 32‐34 . Wan et al 32 proposed a min‐entropy latent model for weakly supervised object detection.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, some researchers proposed several weakly supervised methods to address this issue 32‐34 . Wan et al 32 proposed a min‐entropy latent model for weakly supervised object detection. In their model, the min‐entropy is used for measuring the randomness of object localization which aims to discover the most fitted object position.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A weakly supervised tooth‐mark and crack detection method in tongue image

Hui

Lei

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

Tongue diagnosis is one of the primary clinical diagnostic methods in Traditional Chinese Medicine. Recognizing the tooth-marked tongue and the crackled tongue plays an essential role in evaluating the status of patients. Previous methods mainly focus on identifying whether a tongue image is a tooth-marked tongue (cracked tongue)or not, while cannot provide more details. In this study, we propose a weakly supervised method for training the tooth-mark and crack detection model by leveraging fully bounding-box level annotated and coarse image-level annotated tongue images. The proposed model is extended from the YOLO object detection model, and we add several classification branches for recognizing the tooth-marked tongue and cracked tongue.The classification branch aims to predict the coarse label for both coarse-labeled data and fully annotated data. The detection branch is used to locate the position of tooth marks and cracks from the fully annotated data. Finally, we utilize a multitask loss function for training the model. Experimental results on a challenging tongue image dataset demonstrate the effectiveness of our proposed weakly supervised method.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A weakly supervised tooth‐mark and crack detection method in tongue image

Hui

Lei

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…H UMAN action recognition has been extensively studied in the computer vision community [1]- [9], due to its broad range of applications in human computer interaction, video content analysis, and video surveillance. While many researchers view action recognition in constrained simple backgrounds as a well solved problem, action recognition in real-world complex scenes possess many hurdles driven by the change of human poses, viewpoints, and backgrounds.…”

Section: Introductionmentioning

confidence: 99%

Deep Manifold Structure Transfer for Action Recognition

Zhang

Chen

et al. 2019

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

While intrinsic data structure in subspace provides useful information for visual recognition, it has not yet been well studied in deep feature learning for action recognition. In this paper, we introduce a new spatio-temporal manifold network (STMN) that leverages data manifold structures to regularize deep action feature learning, aiming at simultaneously minimizing the intra-class variations of learned deep features and alleviating the over-fitting problem. To this end, the manifold prior is imposed from the top layer of a convolutional neural network (CNN), and is propagated across convolutional layers during forward-backward propagation. The observed correspondence of manifold structures in the data space and feature space validates that the manifold priori can be transferred across CNN layers. STMN theoretically recasts the problem of transferring the data structure prior into the deep learning architectures as a projection over the manifold via an embedding method, which can be easily solved by an Alternating Direction Method of Multipliers and Backward Propagation (ADMM-BP) algorithm. STMN is generic in the sense that it can be plugged into various backbone architectures to learn more discriminative representation for action recognition. Extensive experimental results show that our method achieves comparable or even better performance as compared with the state-of-the-art approaches on four benchmark datasets.

show abstract

“…In this paper, we propose a new method for pipeline defect detection and deploy a framework of cloud-based pipeline defect detection system. The major work for Pipeline video processing includes image preprocessing, defect location and defect feature recognition [Wang, Chen, Qiao et al (2018); Wan, Wei, Jiao et al (2018)]. In this paper, we preprocess the pipeline image using image grayscale conversion, grayscale stretching, smoothing filter and canny edge detection, then extract the defect feature using histograms of oriented gradients (HOG) and visual geometry group network (VGGNet) [Zhou, Liang, Li et al (2018)], and finally locate and recognize the defect with support vector machine (SVM) [Zhang, Li, Lu et al (2016); Wiatowski and Bolcskei (2018)].…”

Section: Introductionmentioning

confidence: 99%

Pipeline Defect Detection Cloud System Using Role Encryption and Hybrid Information

Li¹,

Shang²,

Zhang³

et al. 2019

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Pipeline defect detection systems collect the videos from cameras of pipeline robots, however the systems always analyzed these videos by offline systems or humans to detect the defects of potential security threats. The existing systems tend to reach the limit in terms of data access anywhere, access security and video processing on cloud. There is in need of studying on a pipeline defect detection cloud system for automatic pipeline inspection. In this paper, we deploy the framework of a cloud based pipeline defect detection system, including the user management module, pipeline robot control module, system service module, and defect detection module. In the system, we use a role encryption scheme for video collection, data uploading, and access security, and propose a hybrid information method for defect detection. The experimental results show that our approach is a scalable and efficient defection detection cloud system.

show abstract

Min-Entropy Latent Model for Weakly Supervised Object Detection

Cited by 207 publications

References 29 publications

A weakly supervised tooth‐mark and crack detection method in tongue image

A weakly supervised tooth‐mark and crack detection method in tongue image

Deep Manifold Structure Transfer for Action Recognition

Pipeline Defect Detection Cloud System Using Role Encryption and Hybrid Information

Contact Info

Product

Resources

About