Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions

Xu, Xin; Li, Guiqing; Xie, Gang; Ren, Jinchang; Xie, Xinlin

doi:10.1155/2019/9180391

Cited by 26 publications

(20 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first is fusion of color, edge and other information for refined segmentation [47,48], and the second is saliency based extraction of objects from images [49,50]. The third direction is deep learning based image segmentation and object detection, where convolutional neural networks and other models will be explored [51,52], even in combination with the first two topics such as multiscale segmentation and extreme learning machines [53,54].…”

Section: Discussionmentioning

confidence: 99%

Weakly Supervised Conditional Random Fields Model for Semantic Segmentation with Image Patches

Xue

Han

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Image semantic segmentation (ISS) is used to segment an image into regions with differently labeled semantic category. Most of the existing ISS methods are based on fully supervised learning, which requires pixel-level labeling for training the model. As a result, it is often very time-consuming and labor-intensive, yet still subject to manual errors and subjective inconsistency. To tackle such difficulties, a weakly supervised ISS approach is proposed, in which the challenging problem of label inference from image-level to pixel-level will be particularly addressed, using image patches and conditional random fields (CRF). An improved simple linear iterative cluster (SLIC) algorithm is employed to extract superpixels. for image segmentation. Specifically, it generates various numbers of superpixels according to different images, which can be used to guide the process of image patch extraction based on the image-level labeled information. Based on the extracted image patches, the CRF model is constructed for inferring semantic class labels, which uses the potential energy function to map from the image-level to pixel-level image labels. Finally, patch based CRF (PBCRF) model is used to accomplish the weakly supervised ISS. Experiments conducted on two publicly available benchmark datasets, MSRC and PASCAL VOC 2012, have demonstrated that our proposed algorithm can yield very promising results compared to quite a few state-of-the-art ISS methods, including some deep learning-based models.

show abstract

Section: Discussionmentioning

confidence: 99%

Weakly Supervised Conditional Random Fields Model for Semantic Segmentation with Image Patches

Xue

Han

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…Only one work [23] covers semantic segmentation. Semantic segmentation in images consists of categorizing each pixel present in the image [4].…”

Section: Rq 1: What Are the Most Common Problems Based On Image Analysis And Datasets Analyzed Under Celm?mentioning

confidence: 99%

Convolutional Extreme Learning Machines: A Systematic Review

Rodrigues¹,

Rogério²,

Kelner³

et al. 2021

Preprint

View full text Add to dashboard Cite

Many works have recently identified the need to combine deep learning with extreme learning to strike a performance balance with accuracy especially in the domain of multimedia applications. Considering this new paradigm, namely convolutional extreme learning machine (CELM), we present a systematic review that investigates alternative deep learning architectures that use extreme learning machine (ELM) for a faster training to solve problems based on image analysis. We detail each of the architectures found in the literature, application scenarios, benchmark datasets, main results, advantages, and present the open challenges for CELM. We follow a well structured methodology and establish relevant research questions that guide our findings. We hope that the observation and classification of such works can leverage the CELM research area providing a good starting point to cope with some of the current problems in the image-based computer vision analysis.

show abstract

“…In supervised learning, annotation quality plays a vital role in training and assessment of the models for several computer vision tasks such as object classification [1,2], detection [3][4][5][6], and segmentation [7][8][9]. e training of object detection models relies on accurate and sufficient annotations.…”

Section: Introductionmentioning

confidence: 99%

Conceptual Cognitive Modeling for Fine-Grained Annotation Quality Assessment of Object Detection Datasets

Guo

Xie

et al. 2020

Discrete Dynamics in Nature and Society

Self Cite

View full text Add to dashboard Cite

In many supervised computer vision tasks such as object detection, manual annotation crowdsourcing platforms are widely used for acquiring large-scale labeled data. However, the annotation quality may suffer low quality that can severely affect the training of models. As a result, the evaluation of the annotations within the dataset is critical, yet it has seldom been addressed in object detection. In this paper, we present a fine-grained annotation quality assessment (FGAQA) framework for evaluating the quality of object detection datasets. First, we formulate a generic annotation quality assessment framework based on the core generalpurpose data quality dimensions, using the bounding box and the label. Second, cognition theory in terms of hierarchy and continuity is utilized to refine the basic framework, including the consistency of the bounding box, completeness of the category, hierarchical accuracy of the label, and the consistency of the label. Comprehensive experiments on the two object detection datasets are used for performance evaluation. It is found that the ground truth annotations of the Urban Traffic Surveillance dataset have more quality issues than the ones of the PASCAL VOC 2007 detection dataset. e proposed FGAQA framework performs an effective fine-grained evaluation of the annotations, which is significant for quality assurance of annotations from crowdsourcing platforms and the subsequent model's training.

show abstract

Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions

Cited by 26 publications

References 37 publications

Weakly Supervised Conditional Random Fields Model for Semantic Segmentation with Image Patches

Weakly Supervised Conditional Random Fields Model for Semantic Segmentation with Image Patches

Convolutional Extreme Learning Machines: A Systematic Review

Conceptual Cognitive Modeling for Fine-Grained Annotation Quality Assessment of Object Detection Datasets

Contact Info

Product

Resources

About