SegNetRes-CRF: A Deep Convolutional Encoder-Decoder Architecture for Semantic Image Segmentation

Oliveira, Luiz Antonio de; Medeiros, Heitor R.; Macêdo, David; Zanchettin, Cleber; Oliveira, Adriano L. I.; Ludermir, Teresa B.

doi:10.1109/ijcnn.2018.8489376

Cited by 10 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Obviously, our goal is to minimize the sum of segmentation loss and representation loss at each training epoch. Specifically, for every labeled image, we take them into the student model to minimize supervised loss by employing Dice Loss in Equation (2). As for each unlabeled images, we take it into the teacher model, where generate pixel-level pseudo-label after selecting reliable pixels and post-processing, and compute unsupervised loss in Equation (3).…”

Section: Methods Architecturementioning

confidence: 99%

“…Effects of various components in LRS 2 . We first use the original semi-segmentation method, without any component, as our basis experiment.…”

Section: Ablation Studiesmentioning

confidence: 99%

“…Accurate segmentation of organs and lesions is of great necessity to construct a computer‐aided diagnosis (CAD) system, which is a vital prerequisite for clinical applications such as diagnosis and surgical planing. In recent years, various full supervised segmentation approaches based on deep learning have made remarkable progress, such as 3D UNet, 1 SegNet, 2 nnUNet, 3 and so forth.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Semi‐supervised liver segmentation based on local regions self‐supervision

Lou,

Lin,

Qian

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundSemi‐supervised learning has gained popularity in medical image segmentation due to its ability to reduce reliance on image annotation. A typical approach in semi‐supervised learning is to select reliable predictions as pseudo‐labels and eliminate unreliable predictions. Contrastive learning helps prevent the insufficient utilization of unreliable predictions, but neglecting the anatomical structure of medical images can lead to suboptimal optimization results.PurposeWe propose a novel approach for semi‐supervised liver segmentation using contrastive learning, which leverages unlabeled data and enhances the suitability of contrastive learning for liver segmentation.Method and materialsContrastive learning helps prevent the inappropriate utilization of unreliable predictions, but neglecting the anatomical structure of medical images can lead to suboptimal optimization results. Therefore, we propose a semi‐supervised contrastive learning method with local regions self‐supervision (LRS2). On one side, we employ Shannon entropy to distinguish between reliable and unreliable predictions and reduce the dissimilarity between their representations within regional artificial units. Within each unit of the liver image, we strongly encourage unreliable predictions to acquire valuable information pertaining to the correct category by leveraging the representations of reliable predictions in their vicinity. On the other side, we introduce a dynamic reliability threshold based on the Shannon entropy of each prediction, gradually evaluating the confidence threshold of reliable predictions as predictive accuracy improves. After selecting reliable predictions, we sequentially apply erosion and dilation to refine them for better selection of qualified positive and negative samples. We evaluate our proposed method on abdominal CT images, including 131 images (train data: 77, validation data: 26, and testing data: 28) from 2017 ISBI Liver Tumors Segmentation Challenge.ResultsOur method obtains satisfactory performance in different proportion by exploiting the unreliable predictions. Compared with the result of VNet only under supervised settings (with 10, 30, 50, 70% and full labeled data), LRS2, respectively, brings an improvement of Dice coefficient by +6.11, +3.55, +4.43, and +2.25%, achieving Dice coefficients of 93.44, 93.31, 94.85, and 95.12%, respectively.ConclusionIn this study, we carefully select appropriate positive and negative samples from reliable regions, ensuring that anchor pixels within unreliable regions are correctly assigned to their respective categories. With a consideration of the anatomical structure present in CT images, we partition the image representations into regional units, enabling anchor pixels to capture more precise sample information. Extensive experiments confirm the effectiveness of our method.

show abstract

Section: Methods Architecturementioning

confidence: 99%

“…Effects of various components in LRS 2 . We first use the original semi-segmentation method, without any component, as our basis experiment.…”

Section: Ablation Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semi‐supervised liver segmentation based on local regions self‐supervision

Lou,

Lin,

Qian

et al. 2023

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Gesture detection using computer vision has recently emerged as a study focus in the community of computer vision applications. De Oliveira Junior [4] employed Hidden Markov Model or HMM to recognize single motions in video, achieving 94 percent identification accuracy across 262 movements. Reyes [5] devised a Dynamic Time Warping or DTW gesture detection approach that accomplishes the detection of depth gesture pictures for video.…”

Section: State Of the Art In Gesture Recognitionmentioning

confidence: 99%

Human Gesture Recognition in Computer Vision Research

Zheng

2022

SHS Web Conf.

View full text Add to dashboard Cite

Human gesture recognition is a popular issue in the studies of computer vision, since it provides technological expertise required to advance the interaction between people and computers, virtual environments, smart surveillance, motion tracking, as well as other domains. Extraction of the human skeleton is a rather typical gesture recognition approach using existing technologies based on two-dimensional human gesture detection. Likewise, I t cannot be overlooked that objects in the surrounding environment give some information about human gestures. To semantically recognize the posture of the human body, the logic system presented in this research integrates the components recognized in the visual environment alongside the human skeletal position. In principle, it can improve the precision of recognizing postures and semantically represent peoples’ actions. As such, the paper suggests a potential and notion for recognizing human gestures, as well as increasing the quantity of information offered through analysis of images to enhance interaction between humans and computers.

show abstract

Hybrid Dilated Convolution Network Using Attentive Kernels for Real-Time Semantic Segmentation

Jiang

Yang

et al. 2020

Pattern Recognition and Computer Vision

View full text Add to dashboard Cite

SegNetRes-CRF: A Deep Convolutional Encoder-Decoder Architecture for Semantic Image Segmentation

Cited by 10 publications

References 14 publications

Semi‐supervised liver segmentation based on local regions self‐supervision

Semi‐supervised liver segmentation based on local regions self‐supervision

Human Gesture Recognition in Computer Vision Research

Hybrid Dilated Convolution Network Using Attentive Kernels for Real-Time Semantic Segmentation

Contact Info

Product

Resources

About