Feedback Convolutional Neural Network for Visual Localization and Segmentation

Cao, Chunshui; Huang, Yongzhen; Yang, Yi; Wang, Liang; Wang, Zhong Lin; Tan, Tieniu

doi:10.1109/tpami.2018.2843329

Cited by 30 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decade, feedback mechanisms have been successfully incorporated into artificial neural networks to accomplish a variety of visual tasks, including saliency detection [39], pose estimation [40], object recognition [41], and visual segmentation [42]. In addition, they have also been used extensively in control theory to solve the stability problem of nonlinear systems [52]- [54].…”

Section: B Feedback Mechanismmentioning

confidence: 99%

See 1 more Smart Citation

A Time-Delay Feedback Neural Network for Discriminating Small, Fast-Moving Targets in Complex Dynamic Environments

Wang

Zhao

et al. 2023

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Discriminating small moving objects within complex visual environments is a significant challenge for autonomous micro robots that are generally limited in computational power. By exploiting their highly evolved visual systems, flying insects can effectively detect mates and track prey during rapid pursuits, even though the small targets equate to only a few pixels in their visual field. The high degree of sensitivity to small target movement is supported by a class of specialized neurons called small target motion detectors (STMDs). Existing STMDbased computational models normally comprise four sequentially arranged neural layers interconnected via feedforward loops to extract information on small target motion from raw visual inputs. However, feedback, another important regulatory circuit for motion perception, has not been investigated in the STMD pathway and its functional roles for small target motion detection are not clear. In this paper, we propose an STMD-based neural network with feedback connection (Feedback STMD), where the network output is temporally delayed, then fed back to the lower layers to mediate neural responses. We compare the properties of the model with and without the time-delay feedback loop, and find it shows preference for high-velocity objects. Extensive experiments suggest that the Feedback STMD achieves superior detection performance for fast-moving small targets, while significantly suppressing background false positive movements which display lower velocities. The proposed feedback model provides an effective solution in robotic visual systems for detecting fast-moving small targets that are always salient and potentially threatening. Index Terms-Neural system modeling, visual neural systems, small target motion detection, time-delay feedback, complex background. I. INTRODUCTION

show abstract

Section: B Feedback Mechanismmentioning

confidence: 99%

“…Feedback mechanisms have been shown to be effective in improving model performance for a number of computer vision tasks, such as saliency detection [39], pose estimation [40], object recognition [41], and visual segmentation [42]. Biological research has also identified various feedback loops in the visual systems of insects [43]- [46].…”

mentioning

confidence: 99%

A Time-Delay Feedback Neural Network for Discriminating Small, Fast-Moving Targets in Complex Dynamic Environments

Wang

Zhao

et al. 2023

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…In this paper, the Dice ratio algorithm is used to evaluate the accuracy of the segmentation result, which indicates the similarity between the experimental segmentation result and the expert manual segmentation gold standard. The images of the MRI modes used in this paper are from the BRATS [47–50] contest, which contains the four modes T1, T1c, T2, and FLAIR. The training data contain 30 patients' real datasets and 50 simulated patient datasets.…”

Section: Experimental Analysismentioning

confidence: 99%

“…The comparison between the method proposed in this paper and other methods in the BRATS [49, 50] contest is shown in Table 1. This paper selects the best performing Zhao method (the Monte Carlo random-based supervoxel clustering method), the Baner method, the ordinary Menze algorithm, and the CNN method as the comparison objects.…”

Section: Experimental Analysismentioning

confidence: 99%

Medical Image Segmentation Algorithm Based on Feedback Mechanism CNN

Liu

2019

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

With the development of computer vision and image segmentation technology, medical image segmentation and recognition technology has become an important part of computer-aided diagnosis. The traditional image segmentation method relies on artificial means to extract and select information such as edges, colors, and textures in the image. It not only consumes considerable energy resources and people’s time but also requires certain expertise to obtain useful feature information, which no longer meets the practical application requirements of medical image segmentation and recognition. As an efficient image segmentation method, convolutional neural networks (CNNs) have been widely promoted and applied in the field of medical image segmentation. However, CNNs that rely on simple feedforward methods have not met the actual needs of the rapid development of the medical field. Thus, this paper is inspired by the feedback mechanism of the human visual cortex, and an effective feedback mechanism calculation model and operation framework is proposed, and the feedback optimization problem is presented. A new feedback convolutional neural network algorithm based on neuron screening and neuron visual information recovery is constructed. So, a medical image segmentation algorithm based on a feedback mechanism convolutional neural network is proposed. The basic idea is as follows: The model for obtaining an initial region with the segmented medical image classifies the pixel block samples in the segmented image. Then, the initial results are optimized by threshold segmentation and morphological methods to obtain accurate medical image segmentation results. Experiments show that the proposed segmentation method has not only high segmentation accuracy but also extremely high adaptive segmentation ability for various medical images. The research in this paper provides a new perspective for medical image segmentation research. It is a new attempt to explore more advanced intelligent medical image segmentation methods. It also provides technical approaches and methods for further development and improvement of adaptive medical image segmentation technology.

show abstract

“…One commonly used strategy is to learn a powerful deep network for visual feature extraction by pretraining on large datasets in a source task, and then adapt this pretrained network to the target task by fine-tuning on a small-size annotated dataset. This idea has been successfully applied to visual recognition [16] and language comprehension [17]. In the medical image domain, transfer learning has also been widely used in image classification and recognition tasks, such as tumor classification [18], [19], retinal diseases diagnosis [20], pneumonia detection [21], lung nodule detection [22] and skin lesion classification [23], [24].…”

mentioning

confidence: 99%

Learning from Pseudo Lesion: A Self-supervised Framework for COVID-19 Diagnosis

Li¹,

Jin²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

The Coronavirus disease 2019 has rapidly spread all over the world since its first report in December 2019 and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based approaches have shown impressive performance in myriad image recognition tasks. However, they usually require a large number of annotated data for training. Inspired by Ground Glass Opacity (GGO), a common finding in COIVD-19 patient's CT scans, we proposed in this paper a novel self-supervised pretraining method based on pseudo lesions generation and restoration for COVID-19 diagnosis. We used Perlin noise, a gradient noise based mathematical model, to generate lesion-like patterns, which were then randomly pasted to the lung regions of normal CT images to generate pseudo COVID-19 images. The pairs of normal and pseudo COVID-19 images were then used to train an encoder-decoder architecture based U-Net for image restoration, which does not require any labelled data. The pretrained encoder was then fine-tuned using labelled data for COVID-19 diagnosis task. Two public COVID-19 diagnosis datasets made up of CT images were employed for evaluation. Comprehensive experimental results demonstrated that the proposed self-supervised learning approach could extract better feature representation for COVID-19 diagnosis and the accuracy of the proposed method outperformed the supervised model pretrained on large scale images by 6.57% and 3.03% on SARS-CoV-2 dataset and Jinan COVID-19 dataset, respectively.

show abstract

Feedback Convolutional Neural Network for Visual Localization and Segmentation

Cited by 30 publications

References 26 publications

A Time-Delay Feedback Neural Network for Discriminating Small, Fast-Moving Targets in Complex Dynamic Environments

A Time-Delay Feedback Neural Network for Discriminating Small, Fast-Moving Targets in Complex Dynamic Environments

Medical Image Segmentation Algorithm Based on Feedback Mechanism CNN

Learning from Pseudo Lesion: A Self-supervised Framework for COVID-19 Diagnosis

Contact Info

Product

Resources

About