IC9600: A Benchmark Dataset for Automatic Image Complexity Assessment

Feng, Tinglei; Zhai, Yingjie; Yang, Jufeng; Liang, Jie; Fan, Deng-Ping; Zhang, Jing; Shao, Ling; Tao, Dacheng

doi:10.1109/tpami.2022.3232328

Cited by 8 publications

(3 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several limitations to this study that should be acknowledged. First, the amount of data used in this study is relatively limited compared to some large computer vision task datasets [38][39][40]. Therefore, we employed a five-fold cross-validation strategy during the training and testing of the classification neural network (Dataset A) to maximize data utilization and ensure a thorough evaluation of its performance.…”

Section: Discussionmentioning

confidence: 99%

Identification of Adolescent Menarche Status using Biplanar X-ray Images: A Deep Learning-based Method

XIE

Xiao

et al. 2023

Bioengineering

View full text Add to dashboard Cite

The purpose of this study is to develop an automated method for identifying the menarche status of adolescents based on EOS radiographs. We designed a deep-learning-based algorithm that contains a region of interest detection network and a classification network. The algorithm was trained and tested on a retrospective dataset of 738 adolescent EOS cases using a five-fold cross-validation strategy and was subsequently tested on a clinical validation set of 259 adolescent EOS cases. On the clinical validation set, our algorithm achieved accuracy of 0.942, macro precision of 0.933, macro recall of 0.938, and a macro F1-score of 0.935. The algorithm showed almost perfect performance in distinguishing between males and females, with the main classification errors found in females aged 12 to 14 years. Specifically for females, the algorithm had accuracy of 0.910, sensitivity of 0.943, and specificity of 0.855 in estimating menarche status, with an area under the curve of 0.959. The kappa value of the algorithm, in comparison to the actual situation, was 0.806, indicating strong agreement between the algorithm and the real-world scenario. This method can efficiently analyze EOS radiographs and identify the menarche status of adolescents. It is expected to become a routine clinical tool and provide references for doctors’ decisions under specific clinical conditions.

show abstract

Section: Discussionmentioning

confidence: 99%

Identification of Adolescent Menarche Status using Biplanar X-ray Images: A Deep Learning-based Method

XIE

Xiao

et al. 2023

Bioengineering

View full text Add to dashboard Cite

show abstract

“…To generate a high-quality prompt, we employ a salient object detector to infer the salient object of a simple-scene image from the group of images. To select the simple-scene image, we adopt the IC algorithm [4] to compute the complexity of images within the group. The lowest-complexity image is chosen as the prompt image, which is detected by ICON [5], which is a salient object detector, to generate the prompt segmentation.…”

Section: Methodsmentioning

confidence: 99%

“…1: Overview of the framework. The input images are first input in the IC [4] algorithm to select the simple-scene image, which is followed by a salient object detector, i.e., ICON [5], to generate the prompt. On top of that, the prompt image and saliency map are fed in SegGPT [3] to predict the co-salient objects in all target images to infer the co-salient maps.…”

Section: Methodsmentioning

confidence: 99%

Disentangled Capsule Routing for Fast Part-Object Relational Saliency

Liu

Zhang²,

Liu

et al. 2022

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Recently, the Part-Object Relational (POR) saliency underpinned by the Capsule Network (CapsNet) has been demonstrated to be an effective modeling mechanism to improve the saliency detection accuracy. However, it is widely known that the current capsule routing operations have huge computational complexity, which seriously limited the usability of the POR saliency models in real-time applications. To this end, this paper takes an early step towards a fast POR saliency inference by proposing a novel disentangled part-object relational network. Concretely, we disentangle horizontal routing and vertical routing from the original omnidirectional capsule routing, thus generating Disentangled Capsule Routing (DCR). This mechanism enjoys two advantages. On one hand, DCR that disentangles orthogonal 1D (i.e., vertical and horizontal) routing greatly reduces parameters and routing complexity, resulting in much faster inference than omnidirectional 2D routing adopted by existing CapsNets. On the other hand, thanks to the light POR cues explored by DCR, we could conveniently integrate the part-object routing process to different feature layers in CNN, rather than just applying it to the small-scaled one as in previous works. This helps to increase saliency inference accuracy. Compared to previous POR saliency detectors, DPORTNet infers visual saliency (5 ∼ 9) × faster, and is more accurate. DPORTNet is available under the open-source license at https://github.com/liuyi1989/DCR.

show abstract