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 901–1,000 of 1,227
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
Comparison of Pre-Trained CNNs for Audio Classification Using Transfer Learning
Tsalera, E., Papadakis, A., & Samarakou, M. (2021) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan10040072 · Cited by 127
“Xception, the Extreme Inception convolutional neural network, is based on Inception-v3 and replaced inception modules with depthwise separable convolution layers, showing improvement in accuracy [31].”
MethodDeep learning based short-term air traffic flow prediction considering temporal–spatial correlation
Lin, Y., Zhang, J., & Liu, H. (2019) · Aerospace Science and Technology · doi:10.1016/j.ast.2019.04.021 · Cited by 145
Bhuiyan, A., Wong, T. Y., Ting, D. S. W., Govindaiah, A., Souied, E. H., & Smith, R. T. (2020) · Translational Vision Science & Technology · doi:10.1167/tvst.9.2.25 · Cited by 138
“30,32 This model is an ensemble of five networks of different input sizes of “Inception-V3” proposed by Szegedy et al., 39 “Inception-Resnet-V2” proposed by Szegedy et al., 40 and “Xception”proposed by Chollet 41 as described in our paper.”
EDLDR: An Ensemble Deep Learning Technique for Detection and Classification of Diabetic Retinopathy
Mondal, S. S., Mandal, N., Singh, K. K., Singh, A., & Izonin, I. (2022) · Diagnostics · doi:10.3390/diagnostics13010124 · Cited by 127
PlantDet: A Robust Multi-Model Ensemble Method Based on Deep Learning For Plant Disease Detection
Shovon, M. S. H., Mozumder, S. J., Pal, O. K., Mridha, M. F., Asai, N., & Shin, J. (2023) · IEEE Access · doi:10.1109/access.2023.3264835 · Cited by 147
“Xception: It [36] is an effective, pre-trained algorithm that was created using the ImageNet dataset as its basis.”
MethodZhang, J., Shao, Z., Ding, Q., Huang, X., Wang, Y., Zhou, X., & Li, D. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3300533 · Cited by 168
Wang, Y., Yang, L., Liu, X., & Yan, P. (2024) · Scientific Reports · doi:10.1038/s41598-024-60375-1 · Cited by 168
Edge Intelligence: Challenges and Opportunities of Near-Sensor Machine Learning Applications
Plastiras, G., Terzi, M., Kyrkou, C., & Theocharides, T. (2018) · 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap.2018.8445118 · Cited by 126
Ship Classification in High-Resolution SAR Images Using Deep Learning of Small Datasets
Wang, Y., Wang, C., & Zhang, H. (2018) · Sensors · doi:10.3390/s18092929 · Cited by 135
Torres, D. L., Feitosa, R. Q., Happ, P. N., Rosa, L. E. C. L., Marcato, J., Martins, J. A. C., Bressan, P. O., Gonçalves, W. N., & Liesenberg, V. (2020) · Sensors · doi:10.3390/s20020563 · Cited by 147
“Furthermore, the DeepLabv3+ version modifies the Xception model presented in [50], replacing all max-pooling operations by depthwise separable convolutions [48].”
MethodColorectal Histology Tumor Detection Using Ensemble Deep Neural Network
Ghosh, S., Bandyopadhyay, A., Sahay, S., Ghosh, R., Kundu, I., & Santosh, K. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104202 · Cited by 138
Skin Cancer Disease Detection Using Transfer Learning Technique
Rashid, J., Ishfaq, M., Ali, G., Saeed, M. R., Hussain, M., Alkhalifah, T., Alturise, F., & Samand, N. (2022) · Applied Sciences · doi:10.3390/app12115714 · Cited by 152
“As discussed in [71], other efficient networks, such as ShuffleNet [72] and Xception [73], utilize the depthwise separable convolution.”
Recent advances in plant disease severity assessment using convolutional neural networks
Shi, T., Liu, Y., Zheng, X., Hu, K., Huang, H. M., Liu, H., & Huang, H. (2023) · Scientific Reports · doi:10.1038/s41598-023-29230-7 · Cited by 174
A review on the application of computer vision and machine learning in the tea industry
Wang, H., Gu, J., & Wang, M. (2023) · Frontiers in Sustainable Food Systems · doi:10.3389/fsufs.2023.1172543 · Cited by 145
“To improve the efficiency of DL network work, researchers have introduced depthwise separable convolution in the networks, typically including MobileNets (Howard et al., 2017), MobilenetV2 (Sandler et al., 2018), and Xception (Chollet, 2017) networks.”
MethodA Robust GAN-Generated Face Detection Method Based on Dual-Color Spaces and an Improved Xception
Chen, B., Liu, X., Zheng, Y., Zhao, G., & Shi, Y.-Q. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3116679 · Cited by 125
“In this section, first, some related studies that use multiple color spaces for generated face detection and the network benchmark Xception [35] model are investigated; then, CBAM [38, 39] is introduced.”
BackgroundMethodInfluentialA General Decoupled Learning Framework for Parameterized Image Operators
Fan, Q., Chen, D., Yuan, L., Hua, G., Yu, N., & Chen, B. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2925793 · Cited by 177
MDCN: Multi-Scale Dense Cross Network for Image Super-Resolution
Li, J., Fang, F., Li, J., Mei, K., & Zhang, G. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3027732 · Cited by 134
SANet: A Slice-Aware Network for Pulmonary Nodule Detection
Mei, J., Cheng, M., Xu, G., Wan, L.-R., & Zhang, H. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3065086 · Cited by 169
Deep learning for reduced order modelling and efficient temporal evolution of fluid simulations
Pant, P., Doshi, R., Bahl, P., & Farimani, A. B. (2021) · Physics of Fluids · doi:10.1063/5.0062546 · Cited by 137
“For our convolutional layers we make use of depth-wise separable convolutions [Chollet, 2017, Szegedy et al., 2015].”
MLFNet: Multi-Level Fusion Network for Real-Time Semantic Segmentation of Autonomous Driving
Fan, J., Wang, F., Chu, H., Hu, X., Cheng, Y., & Gao, B. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3176860 · Cited by 133
A hybrid deep learning pavement crack semantic segmentation
Al‐Huda, Z., Peng, B., Algburi, R. N. A., Al–antari, M. A., AL-Jarazi, R. S., & Zhai, D. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106142 · Cited by 137
Cocoa plantations are associated with deforestation in Côte d’Ivoire and Ghana
Kalischek, N., Lang, N., Renier, C., Daudt, R. C., Addoah, T., Thompson, W. J., Blaser, W. J., Garrett, R. D., Schindler, K., & Wegner, J. D. (2023) · Nature Food · doi:10.1038/s43016-023-00751-8 · Cited by 168
Ahmad, A., Gamal, A. E., & Saraswat, D. (2023) · IEEE Access · doi:10.1109/access.2023.3240100 · Cited by 125
HydraNets: Specialized Dynamic Architectures for Efficient Inference
Shazeer, N., Fatahalian, K., Mark, W. R., & Mullapudi, R. T. (2018) · 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.2018.00843 · Cited by 186
“The hyper parameters k, nb and the point to branch were chosen empirically by searching over nb = [5, 10, 20, 25], k = [3, 4, 5] and branching at block 2 or block 3.”
MethodDeep Learning for Spatially Explicit Prediction of Synoptic-Scale Fronts
Lagerquist, R., McGovern, A., & Gagne, D. J. (2019) · Weather and Forecasting · doi:10.1175/waf-d-18-0183.1 · Cited by 139
Ciftci, U. A., Demir, I., & Yin, L. (2020) · 2020 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304909 · Cited by 115
“In this case, our method outperforms even the most complex network, Xception [20], with more than 10% accuracy.”
MethodTransfer Learning for Automatic Brain Tumor Classification Using MRI Images
Arbane, M., Benlamri, R., Brik, Y., & Djerioui, M. (2021) · International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH) · doi:10.1109/ihsh51661.2021.9378739 · Cited by 147
“The proposed model is implemented on three pre-trained deep CNN models: ResNet [6], Xception [7] and MobilNet-V2 [8], to classify MRI images into “Tumor” or ‘’ Non-tumor’.”
BackgroundMethodA Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution
Park, K., Soh, J. W., & Cho, N. I. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3134172 · Cited by 149
Showkat, S., & Qureshi, S. (2022) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2022.104534 · Cited by 161
“Popular pre-trained models for feature extraction in images include AlexNet [25], VGG [26], SqueezeNet [27], DenseNet [28], MobileNet [29], Inception [30], GoogLeNet [31], Xception [32], ResNet [33], and Ef fi cientNet [34] with architectural variations existing in model versions.”
Chest X-ray analysis empowered with deep learning: A systematic review
Meedeniya, D., Kumarasinghe, H., Kolonne, S., Fernando, C., Díez, I. D. L. T., & Marques, G. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109319 · Cited by 153
Mesías-Ruiz, G. A., Pérez‐Ortiz, M., Dorado, J., de Castro, A. I., & Peña, J. M. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1143326 · Cited by 163
Sharma, V., Nillmani, Gupta, S. K., & Shukla, K. K. (2023) · Intelligent Medicine · doi:10.1016/j.imed.2023.06.001 · Cited by 166
Intelligent Pneumonia Identification From Chest X-Rays: A Systematic Literature Review
Khan, W., Zaki, N., & Ali, L. (2021) · IEEE Access · doi:10.1109/access.2021.3069937 · Cited by 154
Li, M., Liu, Y., Xue, G., Huang, Y., & Yang, G. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3218284 · Cited by 135
Cardellicchio, A., Ruggieri, S., Nettis, A., Renò, V., & Uva, G. (2023) · Engineering Failure Analysis · doi:10.1016/j.engfailanal.2023.107237 · Cited by 131
An Xception Convolutional Neural Network for Malware Classification with Transfer Learning
Lo, W. W., Yang, X., & Wang, Y. (2019) · 2019 10th IFIP International Conference on New Technologies, Mobility and Security (NTMS) · doi:10.1109/ntms.2019.8763852 · Cited by 122
“The Xception model [14] was proposed by Google, Inc.”
MethodElguindi, S., Zeléfsky, M. J., Jiang, J., Veeraraghavan, H., Deasy, J. O., Hunt, M. A., & Tyagi, N. (2019) · Physics and Imaging in Radiation Oncology · doi:10.1016/j.phro.2019.11.006 · Cited by 131
“[20] and then refines it for segmentation using dilated convolutions, which can be applied at varying rates to encode features at different spatial resolutions without reducing the dimensions of the feature space.”
BackgroundRecurrent neural networks can explain flexible trading of speed and accuracy in biological vision
Spoerer, C. J., Kietzmann, T. C., Mehrer, J., Charest, I., & Kriegeskorte, N. (2020) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1008215 · Cited by 121
Proposal-Free Video Grounding with Contextual Pyramid Network
Li, K., Guo, D., & Wang, M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i3.16285 · Cited by 161
“After that, four depthwise separable convolution layers (Chollet 2017) in a stacked block are implemented for local context modelling; and then multi-head self-attention (Seo et al. 2017) is employed to build the long-range dependence in each feature sequence.”
MethodLightweight Inception Networks for the Recognition and Detection of Rice Plant Diseases
Chen, J., Chen, W., Zeb, A., Yang, S., & Zhang, D. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3182304 · Cited by 142
ADD-Net: An Effective Deep Learning Model for Early Detection of Alzheimer Disease in MRI Scans
Fareed, M. M. S., Zikria, S., Ahmed, G., Mui-zzud-din, Mahmood, S., Aslam, M., Jilani, S. F., Moustafa, A., & Asad, M. (2022) · IEEE Access · doi:10.1109/access.2022.3204395 · Cited by 163
“four different pre-trained models like InceptionV3, Xcep161 tion [42], MobileNetV2 [43], and VGG19 [25] to analyze the 162 performance of themodel.”
MethodLatif, S., Boulila, W., Koubâa, A., Zou, Z., & Ahmad, J. E. (2023) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2023.103784 · Cited by 144
Lou, M., Zhang, S., Zhou, H.-Y., Yang, S., Wu, C., & Yu, Y. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3550979 · Cited by 203
“It is worth noting that we use a similar architectural design, with the only di ff erence being the token mixer used, namely, Sep Conv [61], SRA [30], Shifted Win-dow [4], Mixing block [8], ACmix block [7], and our D-Mixer.”
Multimodal Emotion Recognition Based on Facial Expressions, Speech, and EEG
Pan, J., Fang, W., Zhang, Z., Chen, B., Zhang, Z., & Wang, S. (2024) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2023.3240280 · Cited by 121
3D U$$^2$$-Net: A 3D Universal U-Net for Multi-domain Medical Image Segmentation
Huang, C., Han, H., Yao, Q., Zhu, S., & Zhou, S. K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32245-8_33 · Cited by 148
Khalifa, N. E. M., Taha, M. H. N., Ezzat, D., Słowik, A., & Hassanien, A. E. (2020) · IEEE Access · doi:10.1109/access.2020.2970210 · Cited by 133
ESResNet: Environmental Sound Classification Based on Visual Domain Models
Guzhov, A., Raue, F., Hees, J., & Dengel, A. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9413035 · Cited by 110
Helbich, M., Poppe, R. W., Oberski, D. L., van Emmichoven, M. J. Z., & Schram, R. D. (2021) · Landscape and Urban Planning · doi:10.1016/j.landurbplan.2021.104181 · Cited by 127
An innovative deep anomaly detection of building energy consumption using energy time-series images
Copiaco, A., Himeur, Y., Amira, A., Mansoor, W., Fadli, F., Atalla, S., & Sohail, S. S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105775 · Cited by 142
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., & Sang, N. (2018) · arXiv · doi:10.48550/arxiv.1808.00897 · Cited by 193
Detect and locate: Exposing face manipulation by semantic-and noise-level telltales
Kong, C., Chen, B., Li, H., Wang, S., Rocha, A., & Kwong, S. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3169921 · Cited by 120
“We employ the Xception network [33] as the backbone to learn multi-scale feature maps based on two insights.”
MethodAn intelligent fire detection approach through cameras based on computer vision methods
Wu, H., Wu, D., & Zhao, J. (2019) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2019.05.016 · Cited by 131
Fd-Mobilenet: Improved Mobilenet with a Fast Downsampling Strategy
Qin, Z., Zhang, Z., Chen, X., Wang, C., & Peng, Y. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451355 · Cited by 137
Chang, J., Ko, A., Park, S. M., Choi, S., Kim, K., Kim, S. M., Yun, J. M., Канг, У., Shin, I. H., Shin, J. Y., et al. (2020) · American Journal of Ophthalmology · doi:10.1016/j.ajo.2020.03.027 · Cited by 131
SegGCN: Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel
Lei, H., Akhtar, N., & Mian, A. 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/cvpr42600.2020.01163 · Cited by 155
“Within each ResNet block, we apply our fuzzy spherical kernel with depth-separable convolution [6] to aggregate the context information, which contributes significantly to the network efficiency.”
BackgroundMethodPark, S. J., Kim, G., Oh, Y., Seo, J. B., Lee, S. M., Kim, J. H., Moon, S.-J., Lim, J., & Ye, J. C. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102299 · Cited by 139
Toward autonomous laboratories: Convergence of artificial intelligence and experimental automation
Xie, Y., Sattari, K., Zhang, C., & Lin, J. (2022) · Progress in Materials Science · doi:10.1016/j.pmatsci.2022.101043 · Cited by 145
WSS-YOLO: An improved industrial defect detection network for steel surface defects
Lu, M. L., Sheng, W., Zou, Y. Y., Chen, Y., & Chen, Z. (2024) · Measurement · doi:10.1016/j.measurement.2024.115060 · Cited by 144
Are Transformers universal approximators of sequence-to-sequence functions?Preprint
Yun, C., Bhojanapalli, S., Rawat, A. S., Reddi, S. J., & Kumar, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.10077 · Cited by 414
“A depth-wise convolution layer (Sifre & Mallat, 2014; Chollet, 2017; Kaiser et al., 2017) involves convolving each dimension of X with a corresponding convolution filter of size k : where W C ∈ R d × k and ( X ∗ W C ) i, : := X i, : ∗ ( W C ) i, : .”
BackgroundZhang, B., Zhang, Y., & Wang, S. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2919317 · Cited by 128
Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution
Zhang, Q., Jiang, Z., Lu, Q., Han, J., Zeng, Z., Gao, S., & Men, A. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/442 · Cited by 138
Mahmud, T., Paul, B., & Fattah, S. A. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.104119 · Cited by 126
Elgendi, M., Nasir, M. U., Tang, Q., Smith, D., Grenier, J., Batte, C., Spieler, B. M., Leslie, W. D., Menon, C., Fletcher, R., et al. (2021) · Frontiers in Medicine · doi:10.3389/fmed.2021.629134 · Cited by 153
Zhu, X., Li, X., Ong, K., Zhang, W., Li, W., Li, L., Young, D. M., Su, Y., Shang, B., Peng, L., et al. (2021) · Nature Communications · doi:10.1038/s41467-021-23913-3 · Cited by 142
Khozeimeh, F., Sharifrazi, D., Izadi, N. H., Joloudari, J. H., Shoeibi, A., Alizadehsani, R., Górriz, J. M., Hussain, S., Sani, Z. A., Moosaei, H., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-93543-8 · Cited by 126
Zhang, Q., Han, Y., Li, V. O. K., & Lam, J. C. K. (2022) · IEEE Access · doi:10.1109/access.2022.3174853 · Cited by 125
“Although 1x1 convolution layers have already been used for modelling cross-channel correlations [93], few have adopted this structure in deep learning-based air pollution modelling.”
MethodWang, Q., Du, J., Wu, H., Pan, J., Ma, F., & Lee, C. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3256088 · Cited by 171
GFNet: Global Filter Networks for Visual Recognition
Rao, Y., Zhao, W., Zhu, Z. D., Zhou, J., & Lu, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3263824 · Cited by 600
Characterizing the deployment of deep neural networks on commercial edge devices
Hadidi, R., Cao, J., Xie, Y., Asgari, B., Krishna, T., & Kim, H. (2019) · 2019 IEEE International Symposium on Workload Characterization (IISWC) · doi:10.1109/iiswc47752.2019.9041955 · Cited by 118
FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning
Kim, M., Tariq, S., & Woo, S. S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00111 · Cited by 118
“Xception [13]: is considered as the state-of-the-art deep learning model for image classification task.”
BackgroundLiu, Y., Li, Z., Xu, C., Li, J., & Liang, R. (2019) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2019.07.002 · Cited by 127
Dual Machine-Learning System to Aid Glaucoma Diagnosis Using Disc and Cup Feature Extraction
Civit-Masot, J., Domínguez-Morales, M., Vicente-Díaz, S., & Civit, A. (2020) · IEEE Access · doi:10.1109/access.2020.3008539 · Cited by 132
“The comparison networks were VGG16 [30], ResNet50 [41] and Xception [42].”
GBRAS-Net: A Convolutional Neural Network Architecture for Spatial Image Steganalysis
Tabares-Soto, R., Arteaga-Arteaga, H. B., Bravo-Ortíz, M. A., Mora-Rubio, A., Arias-Garzón, D., Alzate-Grisales, J. A., Jacome, A. B., Orozco-Arias, S., Isaza, G. A., & Ramos-Pollán, R. (2021) · IEEE Access · doi:10.1109/access.2021.3052494 · Cited by 143
“These separable convolutions [28] enable residual channel corre-”
BackgroundMitra, A., Mohanty, S. P., Corcoran, P., & Kougianos, E. (2021) · SN Computer Science · doi:10.1007/s42979-021-00495-x · Cited by 146
“We experimented mainly with three networks-Xception [24], InceptionV3 [25], and Resnet50 [26], and finally chose Xception network as the feature extractor.”
MethodNeural Architecture Search for Transformers: A Survey
Chitty-Venkata, K. T., Emani, M., Vishwanath, V., & Somani, A. K. (2022) · IEEE Access · doi:10.1109/access.2022.3212767 · Cited by 118
“Depthwise-Separable Convolution, first introduced in Xception [72] and MobileNet [73], is a sequence of a Depthwise Convolu-tion followed by a Pointwise Convolution to combine the outputs in the depth dimension.”
MethodFault Detection in Solar Energy Systems: A Deep Learning Approach
Duranay, Z. B. (2023) · Electronics · doi:10.3390/electronics12214397 · Cited by 139
A survey of malware detection using deep learning
Bensaoud, A., Kalita, J. K., & Bensaoud, M. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100546 · Cited by 224
Deep learning in automated power line inspection: A review
Faisal, M. A. A., Mecheter, I., Qiblawey, Y., Fernandez, J. H., Chowdhury, M. E. H., & Kiranyaz, S. (2025) · Applied Energy · doi:10.1016/j.apenergy.2025.125507 · Cited by 171
Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions
Naitali, A., Ridouani, M., Salahdine, F., & Kaabouch, N. (2023) · Computers · doi:10.3390/computers12100216 · Cited by 117
“Xception [94], developed by researchers at Google, is an advanced version of the Inception architecture.”
BackgroundAdversarial Threats to DeepFake Detection: A Practical Perspective
Neekhara, P., Dolhansky, B., Bitton, J., & Ferrer, C. C. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00103 · Cited by 117
“For example, state-of-the-art DeepFake classification systems [9, 15, 35] consist of a face-tracking method, following by the cropped face passed on to a CNN-based classifier for classification as Real or Fake [1, 8].”
BackgroundMethodContinuous Gesture Segmentation and Recognition Using 3DCNN and Convolutional LSTM
Zhu, G., Zhang, L., Shen, P., Song, J., Shah, S. A. A., & Bennamoun, M. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2869278 · Cited by 125
A Transfer Learning Method for Pneumonia Classification and Visualization
Luján-García, J. E., Yáñez-Márquéz, C., Villuendas-Rey, Y., & Camacho-Nieto, O. (2020) · Applied Sciences · doi:10.3390/app10082908 · Cited by 133
Automatic recognition of dairy cow mastitis from thermal images by a deep learning detector
Zhang, X., Xi, K., Ningning, F., & Gang, L. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105754 · Cited by 117
A Lightweight Multi-Scale Crossmodal Text-Image Retrieval Method in Remote Sensing
Yuan, Z., Zhang, W., Rong, X., Li, X., Chen, J., Wang, H., Fu, K., & Sun, X. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3124252 · Cited by 150
Gayathri, J. L., Abraham, B., Sujarani, M. S., & Nair, M. S. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.105134 · Cited by 135
LDS-YOLO: A lightweight small object detection method for dead trees from shelter forest
Wang, X., Zhao, Q., Jiang, P., Zheng, Y., Yuan, L., & Yuan, P. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107035 · Cited by 130
LMFFNet: A Well-Balanced Lightweight Network for Fast and Accurate Semantic Segmentation
Shi, M., Shen, J.-L., Yi, Q., Weng, J., Huang, Z., Luo, A., & Zhou, Y. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3176493 · Cited by 124
“The first one introduces the multibranch structure or connects the shallow features and deep features based on the existing backbone networks (e.g., ResNet [13] and Xception [14]).”
MethodInfluentialReview of artificial intelligence-based bridge damage detection
Zhang, Y., & Yuen, K. (2022) · Advances in Mechanical Engineering · doi:10.1177/16878132221122770 · Cited by 142
Toward reliable signals decoding for electroencephalogram: A benchmark study to EEGNeX
Chen, X., Teng, X., Chen, H., Pan, Y., & Geyer, P. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105475 · Cited by 166
Light-Weight RefineNet for Real-Time Semantic SegmentationPreprint
Nekrasov, V., Shen, C., & Reid, I. D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.03272 · Cited by 161
“Alternatively, we might have reverted to recently proposed depthwise separable convo-lutions [10] that are proven to save lots of parameters without sacrificing performance, but our approach is even simpler as it does not use any 3 × 3 convolutions at all, except for the last classification layer.”
MethodA Deep Multi-Modal CNN for Multi-Instance Multi-Label Image Classification
Song, L., Liu, J., Qian, B., Sun, M., Yang, K., Sun, M., & Abbas, S. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2864920 · Cited by 133
Time Domain Audio Visual Speech Separation
Wu, J., Xu, Y., Zhang, S.-X., Chen, L., Yu, M., Xie, L., & Yu, D. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003983 · Cited by 171
Ensemble Meta-Learning for Few-Shot Soot Density Recognition
Gu, K., Zhang, Y., & Qiao, J. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2991208 · Cited by 123
Deep Learning for Feature Extraction in Remote Sensing: A Case-Study of Aerial Scene Classification
Petrovska, B., Zdravevski, E., Lameski, P., Corizzo, R., Štajduhar, I., & Lerga, J. (2020) · Sensors · doi:10.3390/s20143906 · Cited by 124
“We compare pre-trained CNN models InceptionV3 [47], ResNet50 [46], Xception [48], and DenseNet121 for image features used for image scene classification.”
MethodInfluentialDeep Learning Approaches for Detecting COVID-19 From Chest X-Ray Images: A Survey
Alghamdi, H. S., Amoudi, G., Elhag, S., Saeedi, K., & Nasser, J. (2021) · IEEE Access · doi:10.1109/access.2021.3054484 · Cited by 126
“2% accuracy) on the ImageNet dataset [45].”
MethodDeep Malaria Parasite Detection in Thin Blood Smear Microscopic Images
Maqsood, A., Farid, M. S., Khan, M. H., & Grzegorzek, M. (2021) · Applied Sciences · doi:10.3390/app11052284 · Cited by 150
“The Inception-v3 model contains 11 inception modules.”
BackgroundMethodInfluentialTowards Practical Lipreading with Distilled and Efficient Models
Ma, P., Martínez, B., Petridis, S., & Pantić, M. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9415063 · Cited by 150
Broadcasted Residual Learning for Efficient Keyword Spotting
Kim, B., Chang, S., Lee, J., & Sung, D. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-383 · Cited by 188
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.