HCP: A Flexible CNN Framework for Multi-Label Image Classification

Wei, Yunchao; Xia, Wei; Lin, Min; Huang, Junshi; Ni, Bingbing; Dong, Jian; Zhao, Yao; Yan, Shuicheng

doi:10.1109/tpami.2015.2491929

Cited by 602 publications

(322 citation statements)

References 34 publications

Supporting

Mentioning

303

Contrasting

Unclassified

Order By: Relevance

“…Instead of highly utilize the logistic-regression loss or softmax [23] for CNN-based classification, the squared L2 loss function is used [24], [25], [26] and there are many number of methods are available for regression label in the image. There is one direct method is present to measure the total count of pixel of ILD pattern per disease to represents its level of disease [27].…”

Section: Cnn Architecturementioning

confidence: 99%

Pattern classification of interstitial lung disease in high resolution clinical datasets: A systematic review

Atiya¹,

Ramesh²

2018

IJET

View full text Add to dashboard Cite

Automated tissues characterization helps to diagnosis the various diseases including Interstitial lung diseases (ILD). The various features and the several classifiers are used in categorize the different layers depend on the pattern presented in the image. The different types of diseases may occur in the lungs and some of the diseases happen to leave the scars. These scars can be found in the High Resolution Computed Tomography (HRCT) and have different pattern. The different diseases cause the different pattern in the images and these is classified using the efficient classifier that helps to diagnosis the diseases. In this paper, review for the many researches regarding to the classification of the different pattern from the Computed Tomography (CT) images is presented. The evaluation of the efficiency of the methods in terms of classifier and database used for the research is made. The Deep Convolution Neural Network (CNN) provides the promising classifier efficiency compared to the other researches for different pattern. In general, there are five types of pattern is classified: Healthy, ground glass, honeycomb, Fibrosis, and emphysema.

show abstract

Section: Cnn Architecturementioning

confidence: 99%

Pattern classification of interstitial lung disease in high resolution clinical datasets: A systematic review

Atiya¹,

Ramesh²

2018

IJET

View full text Add to dashboard Cite

show abstract

“…CNN-based methods follow the great success of Convolutional Neural Network in other vision tasks, [23], [24], [25], [26], especially semantic segmentation [27], [28], [29]. They leverage the powerful discrimination ability of Convolutional Neural Network (CNN) to extract visual features as inputs of other techniques to produce proposals or directly regress the coordinates of all the object bounding boxes in an image.…”

Section: Related Workmentioning

confidence: 99%

Scale-Aware Pixelwise Object Proposal Networks

Jie

Liang

Feng

et al. 2016

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Abstract-Object proposal is essential for current state-of-the-art object detection pipelines. However, the existing proposal methods generally fail in producing results with satisfying localization accuracy. The case is even worse for small objects which however are quite common in practice. In this paper we propose a novel Scale-aware Pixel-wise Object Proposal (SPOP) network to tackle the challenges. The SPOP network can generate proposals with high recall rate and average best overlap (ABO), even for small objects. In particular, in order to improve the localization accuracy, a fully convolutional network is employed which predicts locations of object proposals for each pixel. The produced ensemble of pixel-wise object proposals enhances the chance of hitting the object significantly without incurring heavy extra computational cost. To solve the challenge of localizing objects at small scale, two localization networks which are specialized for localizing objects with different scales are introduced, following the divide-and-conquer philosophy. Location outputs of these two networks are then adaptively combined to generate the final proposals by a large-/small-size weighting network. Extensive evaluations on PASCAL VOC 2007 show the SPOP network is superior over the state-of-the-art models. The high-quality proposals from SPOP network also significantly improve the mean average precision (mAP) of object detection with Fast-RCNN framework. Finally, the SPOP network (trained on PASCAL VOC) shows great generalization performance when testing it on ILSVRC 2013 validation set.

show abstract

“…Its efficiency and high detection rates make BING a good choice in a large number of successful applications that require category independent object proposals [23][24][25][26][27][28][29]. Recently, deep neural network based object proposal generation methods have become very popular due to their high recall and computational efficiency, e.g., RPN [30], YOLO900 [31], and SSD [32].…”

Section: Introductionmentioning

confidence: 99%

“…Its poor generalization ability has restricted its usage, so RPN is usually only used in object detection. In comparison, BING is based on lowlevel cues concerning enclosing boundaries and thus can produce category independent object proposals, which has demonstrated applications in multi-label image classification [23], semantic segmentation [25], video classification [24], co-salient object detection [29], deep multi-instance learning [26], and video summarisation [27]. However, several researchers [34][35][36][37] have noted that BING's proposal localization is weak.…”

Section: Introductionmentioning

confidence: 99%

BING: Binarized normed gradients for objectness estimation at 300fps

et al. 2019

View full text Add to dashboard Cite

Training a generic objectness measure to produce object proposals has recently become of significant interest. We observe that generic objects with well-defined closed boundaries can be detected by looking at the norm of gradients, with a suitable resizing of their corresponding image windows to a small fixed size. Based on this observation and computational reasons, we propose to resize the window to 8 × 8 and use the norm of the gradients as a simple 64D feature to describe it, for explicitly training a generic objectness measure. We further show how the binarized version of this feature, namely binarized normed gradients (BING), can be used for efficient objectness estimation, which requires only a few atomic operations (e.g., add, bitwise shift, etc.). To improve localization quality of the proposals while maintaining efficiency, we propose a novel fast segmentation method and demonstrate its effectiveness for improving BING's localization performance, when used in multithresholding straddling expansion (MTSE) postprocessing. On the challenging PASCAL VOC2007 dataset, using 1000 proposals per image and intersectionover-union threshold of 0.5, our proposal method achieves a 95.6% object detection rate and 78.6% mean average best overlap in less than 0.005 second per image.

show abstract

HCP: A Flexible CNN Framework for Multi-Label Image Classification

Cited by 602 publications

References 34 publications

Pattern classification of interstitial lung disease in high resolution clinical datasets: A systematic review

Pattern classification of interstitial lung disease in high resolution clinical datasets: A systematic review

Scale-Aware Pixelwise Object Proposal Networks

BING: Binarized normed gradients for objectness estimation at 300fps

Contact Info

Product

Resources

About