Xception: Deep Learning with Depthwise Separable Convolutions
The DOI matches its Crossref record; 20 of the 21 references it cites were found in a registry or an index.
Abstract
We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution can be understood as an Inception module with a maximally large number of towers. This observation leads us to propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions. We show that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset (which Inception V3 was designed for), and significantly outperforms Inception V3 on a larger image classification dataset comprising 350 million images and 17,000 classes. Since the Xception architecture has the same number of parameters as Inception V3, the performance gains are not due to increased capacity but rather to a more efficient use of model parameters.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The top-5 popular baselines adopted in the evaluation are XceptionNet (Chollet 2017), Afchar et al. (2018), Nguyen et al. (2019a), ResNet (He et al. 2016), and Yang et al. (2019b).”
From Countering Malicious DeepFakes: Survey, Battleground, and Horizon (2022) · cites this paper as Chollet 2017
In the citing paper
“The main idea behind Xception is its depthwise separable convolution [125].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [125]
In the citing paper
“Depthwise separable convolution (DSC) has been found in past research to have a smaller number of parameters than traditional convolution [26].”
From Multimodal Emotion Recognition Based on Facial Expressions, Speech, and EEG (2024) · cites this paper as [26]
In the citing paper
“In the research [24], a depthwise separable convolution neural network on FPGA is being reviewed due to its ability to reduce the number of model parameters and improve calculation speeds, which makes it widely used in mobile edge computing applications such as Xception [25] and MobileNet [26].”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [25]
In the citing paper
“For classification (Table 10), the performance of Xception [12], LipForensics [21], Face X-Ray [36], and SBI [56] also drops compared to LAV-DF.”
From AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset (2024) · cites this paper as [12]
5 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“in [4], which our proposed architecture uses extensively.”
BackgroundVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“In 2012, these ideas were refined into the AlexNet architecture [9], where convolution operations were being repeated multiple times in-between max-pooling operations, allowing the network to learn richer features at every spatial scale.”
BackgroundGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 2×
“Since its first introduction, Inception has been one of the best performing family of models on the ImageNet dataset [14], as well as internal datasets in use at Google, in particular JFT [5].”
BackgroundMethodRethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 2×
“What followed was a trend to make this style of network increasingly deeper, mostly driven by the yearly ILSVRC competition; first with Zeiler and Fergus in 2013 [25] and then with the VGG architecture in 2014 [18].”
BackgroundDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · cited 2×
“Since its first introduction, Inception has been one of the best performing family of models on the ImageNet dataset [14], as well as internal datasets in use at Google, in particular JFT [5].”
Background
Research works printed but not linked: 7
- lin, 2013, Network in Network
- sifre, 2014, Rigid-motion scattering for image classification
- silberman, 2016, Tf-slim
- chollet, 2015, Keras
- abadi, 2015, Tensor-Flow Large-scale machine learning on heterogeneous systems
- tieleman, 0, Divide the gradient by a running average of its recent magnitude, COURSERA Neural Networks for Machine Learning, 4
- vanhoucke, 2014, Learning visual representations at scale, ICLRE
Cited by
Items 801–900 of 1,226
A lightweight neural network with strong robustness for bearing fault diagnosis
Yao, D., Liu, H., Yang, J., & Li, X. (2020) · Measurement · doi:10.1016/j.measurement.2020.107756 · Cited by 146
Achour, B., Belkadi, M., Filali, I., Laghrouche, M., & Lahdir, M. (2020) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2020.07.019 · Cited by 162
Diagnosis of skin diseases in the era of deep learning and mobile technology
Göçeri, E. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104458 · Cited by 169
Anti-Forensics for Face Swapping Videos via Adversarial Training
Ding, F., Zhu, G., Li, Y., Zhang, X., Atrey, P. K., & Lyu, S. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3098422 · Cited by 142
Software-hardware co-design for fast and scalable training of deep learning recommendation models
Mudigere, D., Hao, Y., Huang, J., Jia, Z., Tulloch, A., Sridharan, S., Liu, X., Ozdal, M., Nie, J., Park, J., et al. (2022) · Proceedings of the 49th Annual International Symposium on Computer Architecture · doi:10.1145/3470496.3533727 · Cited by 138
Lei, T., Wang, J., Ning, H., Wang, X., Xue, D., Wang, Q., & Nandi, A. K. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3134691 · Cited by 171
Humayun, M., Sujatha, R., Almuayqil, S. N., & Jhanjhi, N. Z. (2022) · Healthcare · doi:10.3390/healthcare10061058 · Cited by 157
“Xception models perform well in convolutional neural networks, and Figure 13 depicts the flow [29].”
BackgroundMethodInfluentialZhu, H., Lin, M., Xu, Z., Yao, Z., Chen, H., Alhudhaif, A., & Alenezi, F. S. (2022) · Information Sciences · doi:10.1016/j.ins.2022.06.091 · Cited by 153
Deep learning-based approaches for robust classification of cervical cancer
Paçal, İ., & Kılıçarslan, S. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08757-w · Cited by 165
Accurate, data-efficient, unconstrained text recognition with convolutional neural networks
Yousef, M., Hussain, K. F., & Mohammed, U. S. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107482 · Cited by 190
A High-Performance CNN Processor Based on FPGA for MobileNets
Wu, D., Zhang, Y., Jia, X., Tian, L., Li, T., Sui, L., Xie, D., & Shan, Y. (2019) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.1109/fpl.2019.00030 · Cited by 177
Detecting Pneumonia Using Convolutions and Dynamic Capsule Routing for Chest X-ray Images
Mittal, A. P., Kumar, D., Mittal, M., Saba, T., Abunadi, I., Rehman, A. U., & Roy, S. S. (2020) · Sensors · doi:10.3390/s20041068 · Cited by 148
“Apart from these studies, there have been works [25,26] that utilized Xception, VGG16, and VGG19 models [27,28] that were pretrained on the ImageNet dataset.”
MethodLi, J., Tang, Y., Zou, X., Lin, G., & Wang, H. (2020) · IEEE Access · doi:10.1109/access.2020.3005386 · Cited by 150
“We finetuned Deeplabv3 from its original structure in [39] by using a publicly pre-trained model [41] and Xception_65 [42] backbone network on our small training dataset.”
MethodObject detection based on an adaptive attention mechanism
Li, W., Liu, K., Zhang, L., & Cheng, F. (2020) · Scientific Reports · doi:10.1038/s41598-020-67529-x · Cited by 166
Blended multi-modal deep convnet features for diabetic retinopathy severity prediction
Bodapati, J. D., Veeranjaneyulu, N., Shareef, S. N., Hakak, S., Bilal, M., Maddikunta, P. K. R., & Jo, O. (2020) · Lancaster EPrints (Lancaster University) · Cited by 141
Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
Behera, A., Wharton, Z., Hewage, P., & Bera, A. (2021) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v35i2.16176 · Cited by 157
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual RecognitionPreprint
Duţă, I. C., Liu, L., Zhu, F., & Shao, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.11538 · Cited by 261
Automated Detection and Forecasting of COVID-19 using Deep Learning Techniques: A Review
Shoeibi, A., Khodatars, M., Jafari, M., Ghassemi, N., Sadeghi, D., Moridian, P., Khadem, A. A., Alizadehsani, R., Hussain, S., Zare, A., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.10785 · Cited by 142
“in linear residual connections around them, except for the first and last modules. Utilizing residual connections in Xception architecture will lead to faster convergence and superior final performance [44]. MOBILENET The novel model called MobileNets is aimed to be used 5 Fig. 10: A typical ResNet architecture used for…”
MethodDeep Neural Network Compression by In-Parallel Pruning-Quantization
Tung, F., & Mori, G. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2886192 · Cited by 140
Hoang, L., Lee, S., Lee, E.-J., & Kwon, K. (2022) · Applied Sciences · doi:10.3390/app12052677 · Cited by 170
OpenEI: An Open Framework for Edge Intelligence
Zhang, X., Wang, Y., Lu, S., Liu, L., xu, L., & Shi, W. (2019) · 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2019.00182 · Cited by 139
“Last, with the support of OpenEI , the edge will need to handle multiple tasks which raises the problem of how to execute multiple tasks on a package in the meantime.”
BackgroundDetecting Photoshopped Faces by Scripting Photoshop
Wang, S.-Y., Wang, O., Zhang, R., Owens, A., & Efros, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01017 · Cited by 135
“(1) FaceForensics++ [31]: A network trained on face swapping and reenactment data; we use the Xception [12] model trained on raw video frames.”
MethodA biological image classification method based on improved CNN
Qin, J., Pan, W., Xiang, X., Tan, Y., & Hou, G. (2020) · Ecological Informatics · doi:10.1016/j.ecoinf.2020.101093 · Cited by 149
ERV-Net: An efficient 3D residual neural network for brain tumor segmentation
Zhou, X., Li, X., Hu, K., Zhang, Y., Chen, Z., & Gao, X. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114566 · Cited by 150
Multi-features extraction based on deep learning for skin lesion classification
Benyahia, S., Meftah, B., & Lézoray, O. (2021) · Tissue and Cell · doi:10.1016/j.tice.2021.101701 · Cited by 168
Advances in Facial Expression Recognition: A Survey of Methods, Benchmarks, Models, and Datasets
Kopalidis, T., Solachidis, V., Vretos, N., & Daras, P. (2024) · Information · doi:10.3390/info15030135 · Cited by 251
Kitaguchi, D., Takeshita, N., Matsuzaki, H., Oda, T., Watanabe, M., Mori, K., Kobayashi, E., & Ito, M. (2020) · International Journal of Surgery · doi:10.1016/j.ijsu.2020.05.015 · Cited by 138
Weakly Labeled Data Augmentation for Deep Learning: A Study on COVID-19 Detection in Chest X-Rays
Rajaraman, S., & Antani, S. (2020) · Diagnostics · doi:10.3390/diagnostics10060358 · Cited by 153
Subramanian, M., Shanmugavadivel, K., & Nandhini, P. S. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07246-w · Cited by 161
“In a nutshell, the Xception architecture is a depth-wise separable convolution layer stack with residual connections [61] and combines ResNets and Inception to create a light, yet high-performance network.”
BackgroundLabel, Verify, Correct: A Simple Few Shot Object Detection Method
Kaul, P., Xie, W., & Zisserman, A. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01384 · Cited by 164
AltFreezing for More General Video Face Forgery Detection
Wang, Z., Bao, J., Zhou, W., Wang, W., & Li, H. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00402 · Cited by 137
“Earlier works [8, 10, 11] mostly focus on searching spatial artifacts.”
BackgroundInfluentialUsing transfer learning to detect galaxy mergers
Ackermann, S., Schawinski, K., Zhang, C., Weigel, A. K., & Turp, M. D. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/sty1398 · Cited by 137
“We will be using the Xception CNN architecture by Chollet (2016) for this paper.”
MethodDeep learning IoT system for online stroke detection in skull computed tomography images
Dourado, C. M. J. D. M., da Silva, S. P. P., da Nóbrega, R. V. M., Barros, A. C. D. S., Filho, P. P. R., & de Albuquerque, V. H. C. (2019) · Computer Networks · doi:10.1016/j.comnet.2019.01.019 · Cited by 141
Tang, P., Liang, Q., Yan, X., Xiang, S., & Zhang, D. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2977013 · Cited by 135
“Inthiswork,theXception[36]structureisusedasthebasicblock (asshowninFig.2)andoriginaldataareusedtotrainthemodel bydefaultifnotspecified.”
MethodHDC-Net: Hierarchical Decoupled Convolution Network for Brain Tumor Segmentation
Luo, Z., Jia, Z., Yuan, Z., & Peng, J. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2998146 · Cited by 147
Disci, R., Gürcan, F., & Soylu, A. (2025) · Cancers · doi:10.3390/cancers17010121 · Cited by 170
D-VAE: A Variational Autoencoder for Directed Acyclic GraphsPreprint
Zhang, M., Jiang, S., Cui, Z., Garnett, R., & Chen, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.11088 · Cited by 232
“Each neural architecture has 6 layers (excluding input and output layers) sampled from: 3× 3 and 5× 5 convolutions, 3× 3 and 5× 5 depthwise-separable convolutions [55], 3 × 3 max pooling, and 3 × 3 average pooling.”
CORE: Consistent Representation Learning for Face Forgery Detection
Ni, Y., Meng, D., Yu, C., Quan, C., Ren, D., & Zhao, Y. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00011 · Cited by 136
“All of our models use Xception [9] as the backbone.”
BackgroundMethodInfluentialHu, Y., Xie, C., Yang, H., Ho, J. W. K., Wen, J., Han, L., Lam, K. O., Wong, Y., Law, S. Y.-K., Chiu, K. W.-H., et al. (2020) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2020.09.014 · Cited by 145
MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
Qiu, Y., Liu, Y., Li, S., & Xu, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i6.16617 · Cited by 157
A New Deep Learning-Based Methodology for Video Deepfake Detection Using XGBoost
Ismail, A., Elpeltagy, M., S. Zaki, M., & Eldahshan, K. (2021) · Sensors · doi:10.3390/s21165413 · Cited by 135
Chen, H., Li, C., Li, X., Rahaman, M. M., Hu, W., Li, Y., Liu, W., Sun, C., Sun, H., Huang, X., et al. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105265 · Cited by 153
A Full-Image Full-Resolution End-to-End-Trainable CNN Framework for Image Forgery Detection
Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2020) · IEEE Access · doi:10.1109/access.2020.3009877 · Cited by 135
A Study on the Detection of Cattle in UAV Images Using Deep Learning
Barbedo, J. G. A., Koenigkan, L. V., Santos, T. T., & Santos, P. M. (2019) · Sensors · doi:10.3390/s19245436 · Cited by 168
“[31] Inception v3 ≥75 × 75 pixels Szegedy et al.”
BackgroundImage classification based on RESNET
Liang, J. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1634/1/012110 · Cited by 182
“Deep convolution neural network has a series of major breakthroughs in image classification[3].”
BackgroundCrack detection using fusion features‐based broad learning system and image processing
Zhang, Y., & Yuen, K. (2021) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12753 · Cited by 138
“In addition, some classical deep CNNs, such as VGG16 (Simonyan & Zisserman, 2014), ResNet50, InceptionV3 (Szegedy et al., 2016), Xception (Chollet, 2017), and Efficientnet (Tan & Le, 2019) were also trained with the following hyperparameters: the initial learning rate is 10 –3 ; the multiplicative factor of learning r…”
BackgroundInfluentialA Survey on Applications of Artificial Intelligence in Fighting Against COVID-19
Chen, J., Li, K., Zhang, Z., Li, K., & Yu, P. S. (2022) · ACM Computing Surveys · doi:10.1145/3465398 · Cited by 135
“The proposed framework integrates 7 DCNN models with different structures, such as VGG19 [183], DenseNet201 [84], ResNetV2 [29], InceptionV3, InceptionResNetV2 [189], Xception [39], and MobileNetV2 [170].”
MethodLu, W., Tao, C., Li, H., Qi, J., & Li, Y. (2022) · Remote Sensing of Environment · doi:10.1016/j.rse.2021.112830 · Cited by 149
xViTCOS: Explainable Vision Transformer Based COVID-19 Screening Using Radiography
Mondal, A. K., Bhattacharjee, A., Singla, P., & Prathosh, A. P. (2021) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2021.3134096 · Cited by 168
Qian, B., Su, J., Wen, Z., Jha, D. N., Li, Y., Guan, Y., Puthal, D., James, P., Yang, R., Zomaya, A. Y., et al. (2021) · ACM Computing Surveys · doi:10.1145/3398020 · Cited by 132
XNOR Neural Engine: A Hardware Accelerator IP for 21.6-fJ/op Binary Neural Network Inference
Conti, F., Schiavone, P. D., & Benini, L. (2018) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2018.2857019 · Cited by 170
“To scale the number of parameters stored in memory in a smooth fashion, we kept the network architecture of mVGG-d fixed, but progressively modified the nature of convolutional layers from the standard definition of (1) in the direction of depthwise separable convolutions [42] following the parameter d.”
MethodA Deep Learning Framework for Driving Behavior Identification on In-Vehicle CAN-BUS Sensor Data
Zhang, J., Wu, Z., Li, F., Xie, C., Ren, T., Chen, J., & Liu, L. (2019) · Sensors · doi:10.3390/s19061356 · Cited by 150
Interleaved Structured Sparse Convolutional Neural Networks
Xie, G., Wang, J., Zhang, T., Lai, J., Hong, R., & Qi, G.-J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00922 · Cited by 130
Automatic grading of human blastocysts from time-lapse imaging
Kragh, M. F., Rimestad, J., Berntsen, J., & Karstoft, H. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.103494 · Cited by 140
RSNet: The Search for Remote Sensing Deep Neural Networks in Recognition Tasks
Wang, J., Zhong, Y., Zheng, Z., Ma, A., & Zhang, L. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3001401 · Cited by 138
Rajpal, S., Lakhyani, N., Singh, A., Kohli, R., & Kumar, N., V (2021) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2021.110749 · Cited by 148
DeepBreastCancerNet: A Novel Deep Learning Model for Breast Cancer Detection Using Ultrasound Images
Raza, A., Ullah, N., Khan, J. A., Assam, M., Guzzo, A., & Aljuaid, H. (2023) · Applied Sciences · doi:10.3390/app13042082 · Cited by 158
Zhang, X., Cheng, S., Wang, L., & Li, H. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3245674 · Cited by 180
“…further reduce computational consumption and memory usage, queries and keys for both X and X are shared so that computation can be reused through transposition operations as follows : We introduced depth-wise separable convolution [51] into the AMCA module to project features into different spaces.”
MethodA Hybrid CNN-LSTM model for Video Deepfake Detection by Leveraging Optical Flow Features
Saikia, P., Dholaria, D., Yadav, P., Patel, V., & Roy, M. (2022) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892905 · Cited by 133
“as, VGG16 [26], InceptionV3 [27], ResNet50 [28], Xception [29], MobileNetV2 [30], EfficientNetB7 [31].”
Ayaz, M., Shaukat, F., & Raja, G. (2021) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-020-00966-0 · Cited by 143
Subdivision-based Mesh Convolution Networks
Hu, S., Liu, Z.-N., Guo, M.-H., Cai, J.-X., Huang, J., Mu, T., & Martin, R. R. (2022) · ACM Transactions on Graphics · doi:10.1145/3506694 · Cited by 192
Husaini, M. A. S. A., Habaebi, M. H., Gunawan, T. S., Islam, M. R., Elsheikh, E. A. A., & Suliman, F. M. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06372-1 · Cited by 133
MRI Deep Learning-Based Solution for Alzheimer’s Disease Prediction
Saratxaga, C. L., Moya, I., Picón, A., Acosta, M., Moreno-Fernández-de-Leceta, A., Garrote, E., & Bereciartua, A. (2021) · Journal of Personalized Medicine · doi:10.3390/jpm11090902 · Cited by 166
“Among the known architectures, the ResNet [45] family has been evaluated, together with Inception [46], Xception [47], etc.”
MethodAn Insulator Defect Detection Model in Aerial Images Based on Multiscale Feature Pyramid Network
Hao, K., Chen, G., Zhao, L., Li, Z., Liu, Y., & Wang, C. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3200861 · Cited by 174
“Finally, to prevent the 344 loss of information caused by upsampling or downsampling 345 in Bi-SimAM-FPN, we introduce the depthwise separable 346 convolution [21] before each feature fusion operation, which 347 Fig.”
MethodLiteEnhanceNet: A lightweight network for real-time single underwater image enhancement
Zhang, S., Zhao, S., An, D., Li, D., & Zhao, R. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122546 · Cited by 133
Lei, L., Yang, Q., Yang, L., Shen, T., Wang, R., & Fu, C. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10775-6 · Cited by 191
A Survey on the Detection and Impacts of Deepfakes in Visual, Audio, and Textual Formats
Mubarak, R., Alsboui, T., Alshaikh, O., Inuwa-Dutse, I., Khan, S., & Parkinson, S. (2023) · IEEE Access · doi:10.1109/access.2023.3344653 · Cited by 132
“Tested on the FaceForensics ++ , Celeb-DF video and ASVSpoof 2019 audio datasets, it sets new benchmarks in all categories, drawing inspiration from the XceptionNet [187] architecture.”
MethodA Robust Attentional Framework for License Plate Recognition in the Wild
Zhang, L., Wang, P., Li, H., Li, Z., Shen, C., & Zhang, Y. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3000072 · Cited by 157
Dynamic Graph Message Passing Networks
Zhang, L., Xu, D., Arnab, A., & Torr, P. H. S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00378 · Cited by 128
Generating 3D People in Scenes Without People
Zhang, Y., Hassan, M. S., Neumann, H., Black, M. J., & Tang, S. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00623 · Cited by 184
CNN with depthwise separable convolutions and combined kernels for rating prediction
Khan, Z. Y., & Niu, Z. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114528 · Cited by 147
Disease and pest infection detection in coconut tree through deep learning techniques
Singh, P. K., Verma, A., & Alex, J. S. R. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.105986 · Cited by 159
A Comprehensive Review of Deep-Learning-Based Methods for Image Forensics
Camacho, I. C., & Wang, K. (2021) · Journal of Imaging · doi:10.3390/jimaging7040069 · Cited by 160
“[89] worked on a full-image CNN based on Xception architecture [90] to detect and localize image falsifications.”
MethodSmart Glass System Using Deep Learning for the Blind and Visually Impaired
Mukhiddinov, M., & Cho, J. (2021) · Electronics · doi:10.3390/electronics10222756 · Cited by 163
“Chollet [53] improved InceptionV3 by replacing a convolution with a depth-wise separable convolution and introduced the Xception model.”
MethodAM³Net: Adaptive Mutual-Learning-Based Multimodal Data Fusion Network
Wang, J., Li, J., Shi, Y., Lai, J., & Tan, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3148257 · Cited by 142
Müller, D., Soto‐Rey, I., & Krämer, F. (2022) · IEEE Access · doi:10.1109/access.2022.3182399 · Cited by 183
“The following architecture were selected: DenseNet121 [47], EfficientNetB4 [41], InceptionResNetV2 [42], MobileNetV2 [48], ResNeXt101 [49], ResNet101 [50], VGG16 [51], Xception [40] and a custom Vanilla architecture for comparison.”
MethodInfluentialAjagbe, S. A., & Adigun, M. O. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15805-z · Cited by 143
IPOD: Intensive Point-based Object Detector for Point Cloud
Yang, Z., Sun, Y., Liu, S., Shen, X., & Jia, J. (2018) · arXiv · doi:10.48550/arxiv.1812.05276 · Cited by 132
“Positive Points Selection For semantic segmentation, which is used for foreground point selection, we use the Deeplab-v3 [3] based on X-ception [5] network trained on Cityscapes [6] due to the lack of semantic segmentation annotation in KITTI dataset.”
MethodKernel Transformer Networks for Compact Spherical Convolution
Su, Y.-C., & Grauman, K. L. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00967 · Cited by 165
“We address the first requirement (size and cost) by employing depthwise separable convolutions [9,18] within the KTN.”
MethodRastogi, P., Khanna, K., & Singh, V. P. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105236 · Cited by 131
Divyanth, L. G., Ahmad, A., & Saraswat, D. (2022) · Smart Agricultural Technology · doi:10.1016/j.atech.2022.100108 · Cited by 159
Ship detection with deep learning: a survey
Er, M. J., Zhang, Y., Chen, J., & Gao, W. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10455-x · Cited by 143
Use of a Capsule Network to Detect Fake Images and Videos
Nguyen, H. H., Yamagishi, J., & Echizen, I. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12467 · Cited by 121
Human activity recognition using wearable sensors by heterogeneous convolutional neural networks
Han, C., Zhang, L., Tang, Y., Huang, W., Min, F., & He, J. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.116764 · Cited by 130
Guo, R., Liu, H., Xie, G., & Zhang, Y. M. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3059860 · Cited by 130
“Introducing Xception to defect detection as a base learner for transfer learning is of great value to study its applicability for industrial image data [27].”
BackgroundMethodBrain Tumor Classification Based on Fine-Tuned Models and the Ensemble Method
Noreen, N., Palaniappan, S., Qayyum, A., Ahmad, I., & Alassafi, M. O. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2021.014158 · Cited by 164
MiniViT: Compressing Vision Transformers with Weight Multiplexing
Zhang, J., Peng, H., Wu, K., Liu, M., Xiao, B., Fu, J., & Yuan, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01183 · Cited by 127
UAV T-YOLO-Rice: An Enhanced Tiny Yolo Networks for Rice Leaves Diseases Detection in Paddy Agronomy
Sangaiah, A. K., Yu, F.-N., Lin, Y., Shen, W.-C., & Sharma, A. (2024) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2024.3350640 · Cited by 155
“Then the input feature maps are multiplied by these two attention maps to obtain subsequently refined feature maps.”
Cross-Dataset Variability Problem in EEG Decoding With Deep Learning
Xu, L., Xu, M., Ke, Y., An, X., Liu, S., & Ming, D. (2020) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2020.00103 · Cited by 129
Semantic scene segmentation in unstructured environment with modified DeepLabV3+
Baheti, B., Innani, S., Gajre, S. S., & Talbar, S. N. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.07.029 · Cited by 142
End-to-end deep learning of lane detection and path prediction for real-time autonomous driving
Lee, D., & Liu, J. (2022) · Signal Image and Video Processing · doi:10.1007/s11760-022-02222-2 · Cited by 158
Deep-learning based detection of COVID-19 using lung ultrasound imagery
Diaz-Escobar, J., Ordóñez-Guillén, N. E., Villarreal‐Reyes, S., Galaviz‐Mosqueda, A., Kober, V. I., Rivera-Rodríguez, R., & Lozano-Rizk, J. E. (2021) · PLoS ONE · doi:10.1371/journal.pone.0255886 · Cited by 133
Marks, M., Qiuhan, J., Sturman, O., von Ziegler, L., Kollmorgen, S., von der Behrens, W., Mante, V., Bohacek, J., & Yanik, M. F. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00477-5 · Cited by 164
Edge Intelligence: Architectures, Challenges, and Applications
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12172 · Cited by 120
Lee, J. H., Ha, E. J., & Kim, J. H. (2019) · European Radiology · doi:10.1007/s00330-019-06098-8 · Cited by 133
Effnet: An Efficient Structure for Convolutional Neural Networks
Freeman, I., Roese-Koerner, L., & Kummert, A. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451339 · Cited by 148
ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks
Saini, R., Jha, N. K., Das, B. K., Mittal, S., & Mohan, C. K. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093341 · Cited by 143
“To reduce the computational cost depthwise separable (DWS) convolution [30, 14, 9] has been deployed which decouples the m × n with sk × sk by decomposing the standard convolution into depthwise convolution (feature extraction) and pointwise convolution (feature aggregation).”
MethodIqbal, I. A., Shahzad, G., Rafiq, N., Mustafa, G., & Ma, J. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.1646 · Cited by 134
Practical Deep Raw Image Denoising on Mobile Devices
Wang, Y., Huang, H., Xu, Q., Liu, J., Liu, Y., & Wang, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58539-6_1 · Cited by 165
Eckardt, J.-N., Middeke, J. M., Riechert, S., Schmittmann, T., Sulaiman, A. S., Kramer, M., Sockel, K., Kroschinsky, F., Schuler, U., Schetelig, J., et al. (2022) · Leukemia · doi:10.1038/s41375-021-01408-w · Cited by 127
Metadata
- Authors
- Chollet, F.
- Affiliations
- Google (United States) (US)
- Corresponding author
- Chollet, Francois
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 1800-1807
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2531409750
- Cited by
- 20,380
- References
- 21
- Citations by year
- 2026: 1618 · 2025: 3098 · 2024: 3287 · 2023: 3281 · 2022: 3003 · 2021: 2735 · 2020: 1859 · 2019: 1096 · 2018: 356 · 2017: 42
- FWCI
- 268.33
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- Xception, depthwise separable convolution, Inception module, InceptionV3, convolutional neural network architecture, image classification, parameter efficiency, ImageNet, large-scale image classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.