Search Results - "Pattern recognition"

U2-Net: Going deeper with nested U-structure for salient object detection by Qin, Xuebin, Zhang, Zichen, Huang, Chenyang, Dehghan, Masood, Zaiane, Osmar R., Jagersand, Martin

“…•A novel ReSidual U-block (RSU) is designed to capture multi-scale deep features.•A nested U-structure, called U2-Net, that uses RSU is developed for salient…”
Get full text

Recent advances in convolutional neural networks by Gu, Jiuxiang, Wang, Zhenhua, Kuen, Jason, Ma, Lianyang, Shahroudy, Amir, Shuai, Bing, Liu, Ting, Wang, Xingxing, Wang, Gang, Cai, Jianfei, Chen, Tsuhan

“…•We give an overview of the basic components of CNN.•We discuss the improvements of CNN on different aspects, namely, layer design, activation function, loss…”
Get full text

Hypergraph convolution and hypergraph attention by Bai, Song, Zhang, Feihu, Torr, Philip H.S.

“…•Hypergraph convolution defines a basic convolutional operator in a hypergraph. It enables an efficient information propagation between vertices by fully…”
Get full text

Wider or Deeper: Revisiting the ResNet Model for Visual Recognition by Wu, Zifeng, Shen, Chunhua, van den Hengel, Anton

“…•We further develop the unravelled view of ResNets, which helps us better understand their behaviours. We demonstrate this in the context of a training…”
Get full text

Understanding adversarial attacks on deep learning based medical image analysis systems by Ma, Xingjun, Niu, Yuhao, Gu, Lin, Wang, Yisen, Zhao, Yitian, Bailey, James, Lu, Feng

“…•Medical image DNNs are easier to be attacked than natural non-medical image DNNs.•Complex biological textures of medical images may lead to more vulnerable…”
Get full text

The impact of class imbalance in classification performance metrics based on the binary confusion matrix by Luque, Amalia, Carrasco, Alejandro, Martín, Alejandro, de las Heras, Ana

“…•Imbalance coefficient fosters measuring imbalance.•Geometric Mean and Bookmaker Informedness constitute the best unbiased metrics.•Matthews Correlation…”
Get full text

Underwater scene prior inspired deep underwater image and video enhancement by Li, Chongyi, Anwar, Saeed, Porikli, Fatih

“…•Underwater image and video synthesis approach is desired by data-driven methods.•Underwater scene prior is helpful for underwater image and video…”
Get full text

Binary neural networks: A survey by Qin, Haotong, Gong, Ruihao, Liu, Xianglong, Bai, Xiao, Song, Jingkuan, Sebe, Nicu

“…•We summarize the binary neural network methods and categorize them into the naive binarization and the optimized binarization.•The binary neural networks are…”
Get full text

3D Object Detection for Autonomous Driving: A Survey by Qian, Rui, Lai, Xin, Li, Xirong

“…•Notice that no recent literature exists to collect the growing knowledge concerning 3D object detection, we fill this gap by starting with several basic…”
Get full text

Sensor-based and vision-based human activity recognition: A comprehensive survey by Minh Dang, L., Min, Kyungbok, Wang, Hanxiang, Jalil Piran, Md, Hee Lee, Cheol, Moon, Hyeonjoon

“…•A comprehensive review of vision-based and sensor-based human activity recognition.•Summarize and discuss public datasets that are used in vision-based HAR…”
Get full text

A Comprehensive Survey of Image Augmentation Techniques for Deep Learning by Xu, Mingle, Yoon, Sook, Fuentes, Alvaro, Park, Dong Sun

“…•We examine challenges and vicinity distribution to demonstrate the necessity of image augmentation for deep learning.•We present a comprehensive survey on…”
Get full text

Explaining nonlinear classification decisions with deep Taylor decomposition by Montavon, Grégoire, Lapuschkin, Sebastian, Binder, Alexander, Samek, Wojciech, Müller, Klaus-Robert

“…Nonlinear methods such as Deep Neural Networks (DNNs) are the gold standard for various challenging machine learning problems such as image recognition…”
Get full text

LLNet: A deep autoencoder approach to natural low-light image enhancement by Lore, Kin Gwn, Akintayo, Adedotun, Sarkar, Soumik

“…In surveillance, monitoring and tactical reconnaissance, gathering visual information from a dynamic environment and accurately processing such data are…”
Get full text

RGB-T object tracking: Benchmark and baseline by Li, Chenglong, Liang, Xinyan, Lu, Yijuan, Zhao, Nan, Tang, Jin

“…•A large-scale RGB-T dataset is contributed to online RGB-T object tracking. The benchmark with a dozen of baseline trackers and 5 evaluation metrics will be…”
Get full text

An effective CNN and Transformer complementary network for medical image segmentation by Yuan, Feiniu, Zhang, Zhengxiao, Fang, Zhijun

“…•We design dual encoding paths of CNN and Transformer encoders for producing complementary features..•We propose an effective feature complementary module by…”
Get full text

Unsupervised domain adaptive re-identification: Theory and practice by Song, Liangchen, Wang, Cheng, Zhang, Lefei, Du, Bo, Zhang, Qian, Huang, Chang, Wang, Xinggang

“…•We introduce the theoretical guarantees of unsupervised domain adaptive re-ID based on [2]. A DA-learnability result is shown under three assumptions that…”
Get full text

A review of methods for imbalanced multi-label classification by Tarekegn, Adane Nega, Giacobini, Mario, Michalak, Krzysztof

“…•Three types of imbalanced problems are common challenges in multi-label classification: imbalance within labels, between labels, and among label-sets.•A…”
Get full text

Multiple instance learning: A survey of problem characteristics and applications by Carbonneau, Marc-André, Cheplygina, Veronika, Granger, Eric, Gagnon, Ghyslain

“…•The characteristics specific of MIL problems are formally identified and described.•MIL methods and applications are reviewed in the light of the problem…”
Get full text

Reconstruction by inpainting for visual anomaly detection by Zavrtanik, Vitjan, Kristan, Matej, Skočaj, Danijel

“…•A reconstruction-by-inpainting-based anomaly detection method (RIAD) was proposed.•RIAD achieves state-of-the-art performance on anomaly detection and…”
Get full text

Deep learning for image-based cancer detection and diagnosis − A survey by Hu, Zilong, Tang, Jinshan, Wang, Ziming, Zhang, Kai, Zhang, Ling, Sun, Qingling

“…In this paper, we aim to provide a survey on the applications of deep learning for cancer detection and diagnosis and hope to provide an overview of the…”
Get full text