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 601–700 of 1,227
Zhou, Z., Zhang, J., & Gong, C. (2023) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13003 · Cited by 175
“The former is composed of the backbone Xception (Chollet, 2017) and atrous spatial pyramid pooling (ASPP) to extract the target feature.”
BackgroundMethodXiao, B., Xu, Y., Bi, X., Zhang, J., & Ma, X. (2020) · Neurocomputing · doi:10.1016/j.neucom.2018.09.101 · Cited by 174
A spatial-channel hierarchical deep learning network for pixel-level automated crack detection
Pan, Y., Zhang, G., & Zhang, L. (2020) · Automation in Construction · doi:10.1016/j.autcon.2020.103357 · Cited by 176
Deep learning to find colorectal polyps in colonoscopy: A systematic literature review
Sánchez-Peralta, L. F., Bote-Curiel, L., Picón, A., Sánchez-Margallo, F. M., & Pagador, J. B. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101923 · Cited by 177
“…[54] compare three detection approaches: (1) hand-crafted global features and a logistic model tree classifier; (2) fine-tuned well-known architectures, such as Xception [109], VGG19 and ResNet50; and (3) a pixel-wise segmentation GAN with a threshold on the number of positively labelled pixels.”
MethodSurvey of Image Edge Detection
Sun, R., Lei, T., Chen, Q., Wang, Z., Du, X., Zhao, W., & Nandi, A. K. (2022) · Frontiers in Signal Processing · doi:10.3389/frsip.2022.826967 · Cited by 172
Islam, M. R., Abdulrazak, L. F., Nahiduzzaman, M., Goni, M. O. F., Anower, M. S., Ahsan, M., Haider, J., & Kowalski, M. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105602 · Cited by 175
Music Source Separation in the Waveform Domain
Défossez, A., Usunier, N., Bottou, L., & Bach, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.13254 · Cited by 175
“…PReLU [He et al., 2015a] non linearity, a layer wise normalization over all channels jointly [Ba et al., 2016], a depth-wise separable convolution [Chollet, 2017, Howard et al., 2017] with a kernel size of 3, a stride of 1 and a dilation of 2 n mod N , with n the 0-based index of the block and N…”
BackgroundDeep semantic segmentation for automated driving: Taxonomy, roadmap and challenges
Siam, M., Elkerdawy, S., Jagersand, M., & Yogamani, S. (2017) · 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2017.8317714 · Cited by 178
Rapid and robust two-dimensional phase unwrapping via deep learning
Zhang, T., Jiang, S., Zhao, Z., Dixit, K., Zhou, X., Hou, J., Zhang, Y., & Yan, C. (2019) · Optics Express · doi:10.1364/oe.27.023173 · Cited by 173
Medical image registration using deep neural networks: A comprehensive review
Boveiri, H. R., Khayami, R., Javidan, R., & Mehdizadeh, A. (2020) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2020.106767 · Cited by 179
Deep learning methods for object detection in smart manufacturing: A survey
Ahmad, H. M., & Rahimi, A. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.06.011 · Cited by 177
Image forgery detection: a survey of recent deep-learning approaches
Zanardelli, M., Guerrini, F., Leonardi, R., & Adami, N. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13797-w · Cited by 176
“[88] In [88], the authors developed a method to detect image DeepFakes that is based upon the XceptionNet architecture proposed by Google in a previous paper [15].”
MethodShaban, M., Khurram, S. A., Fraz, M. M., Alsubaie, N., Masood, I., Mushtaq, S., Hassan, M., Loya, A., & Rajpoot, N. M. (2019) · Scientific Reports · doi:10.1038/s41598-019-49710-z · Cited by 176
Optimization and acceleration of convolutional neural networks: A survey
Habib, G., & Qureshi, S. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2020.10.004 · Cited by 175
Bodapati, J. D., Shaik, N. S., & Naralasetti, V. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02727-z · Cited by 175
“• Extreme version of Inception (Xception) (Chollet 2017): Xception is another deep ConvNet introduced by Google in 2017 as an extended version of Inception.”
BackgroundExplainable artificial intelligence in skin cancer recognition: A systematic review
Hauser, K., Kurz, A., Haggenmüller, S., Maron, R. C., von Kalle, C., Utikal, J. S., Meier, F., Hobelsberger, S., Gellrich, F. F., Sergon, M., et al. (2022) · European Journal of Cancer · doi:10.1016/j.ejca.2022.02.025 · Cited by 175
An Effective Approach to Detect and Identify Brain Tumors Using Transfer Learning
Ullah, N., Khan, J. A., Khan, M. S., Khan, W., Hassan, I., Obayya, M., Negm, N., & Salama, A. S. (2022) · Applied Sciences · doi:10.3390/app12115645 · Cited by 174
“The Xception [39] TL algorithm is 71 layers deep.”
MethodSemantic Segmentation of Litchi Branches Using DeepLabV3+ Model
Peng, H., Xue, C., Shao, Y., Chen, K., Xiong, J., Xie, Z., & Zhang, L. (2020) · IEEE Access · doi:10.1109/access.2020.3021739 · Cited by 172
“The improved Xception (Chollet, [23]) feature extraction model used by DeepLabV3 + has been improved at different depths.”
MethodZhou, G., Chen, W., Gui, Q., Li, X., & Wang, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3128033 · Cited by 171
VTNFP: An Image-Based Virtual Try-On Network With Body and Clothing Feature Preservation
Yu, R., Wang, X., & Xie, X. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01061 · Cited by 168
Deepfake Detection through Deep Learning
Pan, D., Sun, L., Wang, R., Zhang, X., & Sinnott, R. O. (2020) · 2020 IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT) · doi:10.1109/bdcat50828.2020.00001 · Cited by 172
Asif, S., Zhao, M., Tang, F., & Zhu, Y. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14828-w · Cited by 170
A review of UAV autonomous navigation in GPS-denied environments
Chang, Y., Cheng, Y., Manzoor, U., & Murray, J. (2023) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2023.104533 · Cited by 168
Asif, S., Wenhui, Y., ur-Rehman, S., ul-ain, Q., Amjad, K., Yueyang, Y., Jinhai, S., & Awais, M. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-024-10148-w · Cited by 171
Almaraz-Damian, J.-A., Ponomaryov, V., Sadovnychiy, S., & Castillejos-Fernandez, H. (2020) · Entropy · doi:10.3390/e22040484 · Cited by 172
Face Image Quality Assessment: A Literature Survey
Schlett, T., Rathgeb, C., Henniger, O., Galbally, J., Fierrez, J., & Busch, C. (2022) · ACM Computing Surveys · doi:10.1145/3507901 · Cited by 170
“Among the 10 pretrained CNNs, 2 were meant specifically for FIQA (the illumination-focused FIQA [9], and the general FIQA [56]), 3 were mobile networks (MobileNetV2 [178], DenseNet-169 [179], NASNet [180]), and the other 5 were AlexNet [149], VGG-16/VGG-19 [175], Inception [150], and Xception [181].”
Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation
Ghali, R., Akhloufi, M. A., & Mseddi, W. S. (2022) · Sensors · doi:10.3390/s22051977 · Cited by 172
A Transfer Learning and Optimized CNN Based Intrusion Detection System for Internet of Vehicles
Yang, L., & Shami, A. (2022) · ICC 2022 - IEEE International Conference on Communications · doi:10.1109/icc45855.2022.9838780 · Cited by 159
“Xception [19] is an extension of the Inception network that uses depthwise separable convolutions to replace the standard network convolutions.”
F 2 Trans: High-Frequency Fine-Grained Transformer for Face Forgery Detection
Miao, C., Tan, Z., Chu, Q., Liu, H., Hu, H., & Yu, N. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3233774 · Cited by 172
“patch embeddings by the Stem layer, which is composed of a 4×4 non-overlapped convolution, a 7×7 depth-wise separable convolution block [59], [60] and a 1×1 convolution.”
BackgroundDivide and Conquer: A Deep CASA Approach to Talker-Independent Monaural Speaker Separation
Liu, Y., & Wang, D. (2019) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2941148 · Cited by 172
“A depthwise dilated convolutional layer [5] with kernel S ∈ R3×H , followed by PReLU activation and layer normalization, is then employed to capture the temporal context.”
MethodTreeGen: A Tree-Based Transformer Architecture for Code Generation
Sun, Z., Zhu, Q., Xiong, Y., Sun, Y., Mou, L., & Zhang, L. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6430 · Cited by 167
Smith, M. L., Smith, L. N., & Hansen, M. F. (2021) · Computers in Industry · doi:10.1016/j.compind.2021.103472 · Cited by 171
D-former: a U-shaped Dilated Transformer for 3D medical image segmentation
Wu, Y., Liao, K., Chen, J., Wang, J., Chen, D. Z., Gao, H., & Wu, J. (2023) · Neural Computing and Applications · doi:10.1007/s00521-022-07859-1 · Cited by 172
Lei, T., Geng, X., Ning, H., Lv, Z., Gong, M., Jin, Y., & Nandi, A. K. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3261273 · Cited by 168
“The MSDConv is inspired by Xception [17] but is different from it.”
InfluentialDABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation
Li, G., Yun, I., Kim, J., & Kim, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.11357 · Cited by 171
“Xception [7] and MobileNet [13] use the depth-wise separable convolution to reduce the amount of computation with only a slight drop in performance.”
MethodDevil Is in the Edges: Learning Semantic Boundaries From Noisy Annotations
Acuna, D., Kar, A., & Fidler, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01133 · Cited by 162
“Xception 65 [11] vs Resnet101 [17, 36], and further employs a decoder that refines object boundaries [10].”
BackgroundDiabetic Retinopathy Diagnosis From Fundus Images Using Stacked Generalization of Deep Models
Kaushik, H., Singh, D., Kaur, M., Alshazly, H., Zaguia, A., & Hamam, H. (2021) · IEEE Access · doi:10.1109/access.2021.3101142 · Cited by 170
Cao, Y., Pang, D., Zhao, Q., Yan, Y., Jiang, Y., Tian, C., Wang, F., & Li, J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.107866 · Cited by 165
Elharrouss, O., Akbari, Y., Almadeed, N., & Al-Maadeed, S. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2024.100645 · Cited by 163
Deep Learning-Based Transfer Learning for Classification of Skin Cancer
Jain, S., Singhania, U., Tripathy, B., Nasr, E. A., Aboudaif, M. K., & Kamrani, A. K. (2021) · Sensors · doi:10.3390/s21238142 · Cited by 169
“The Xception [47] architecture is an extension of the Inception architecture.”
BackgroundNon-local Social Pooling for Vehicle Trajectory Prediction
Messaoud, K., Yahiaoui, I., Verroust-Blondet, A., & Nashashibi, F. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8813829 · Cited by 169
“We use a (3 × 3) depthwise convolution kernel [29] to capture the dependencies between nearby vehicles.”
MethodVirtual Multi-view Fusion for 3D Semantic Segmentation
Kundu, A., Yin, X., Fathi, A., Ross, D., Brewington, B., Funkhouser, T., & Pantofaru, C. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58586-0_31 · Cited by 167
End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network
Coquenet, D., Chatelain, C., & Paquet, T. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3144899 · Cited by 158
Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy
Majumder, S., & Kehtarnavaz, N. (2021) · IEEE Access · doi:10.1109/access.2021.3109240 · Cited by 169
“The architecture of the Xception model [55] is based on depthwise separable convolution layers and consists of three major sections: entry flow, middle flow, and exit flow.”
MethodLi, D., & Du, L. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10102-3 · Cited by 165
“2017), Xception network (Chollet 2017), and DenseNet (Huang et al.”
BackgroundMethodCOVID-19 image classification using deep learning: Advances, challenges and opportunities
Aggarwal, P., Mishra, N. K., Fatimah, B., Singh, P., Gupta, A., & Joshi, S. D. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105350 · Cited by 168
“It uses depthwise separable convolution from the Xception network with the aim to reduce model complexity and parameters that would compress the network and improve the speed.”
InfluentialAutomatic Ship Classification from Optical Aerial Images with Convolutional Neural Networks
Gallego, A.-J., Pertusa, A., & Gil, P. (2018) · Remote Sensing · doi:10.3390/rs10040511 · Cited by 168
“Xception [40].”
MethodEV-SegNet: Semantic Segmentation for Event-Based Cameras
Alonso, I., & Murillo, A. C. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00205 · Cited by 163
Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation
Hou, Q., & Liu, F. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00423 · Cited by 162
Shaheed, K., Mao, A., Qureshi, I., Kumar, M., Hussain, S., Ullah, I., & Zhang, X. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.116288 · Cited by 168
Ukwuoma, C. C., Qin, Z., Belal Bin Heyat, M., Akhtar, F., Bamisile, O., Muaad, A. Y., Addo, D., & Al-antari, M. A. (2023) · Journal of Advanced Research · doi:10.1016/j.jare.2022.08.021 · Cited by 166
“Xception [57]: This is a stack of the depth-wise separable convolution layers linearly with residual connections.”
BackgroundMethodBringing ai to edge: from deep learning’s perspective
Liu, D., Kong, H., Luo, X., Liu, W., & Subramaniam, R. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.04.141 · Cited by 171
“her prominent DNN models targeting resource-limited devices. MobileNet [43] replaces the conventional convolutional operation with more efficient depth-wise separable convolution operation proposed in [46] to reduce the computational cost. Depth-wise separable convolution operation factorizes a conventional k k n convo…”
BackgroundStudies on Different CNN Algorithms for Face Skin Disease Classification Based on Clinical Images
Wu, Z., Zhao, S., Peng, Y., He, X., Zhao, X., Huang, K., Wu, X., Fan, W., Li, F., Chen, M., et al. (2019) · IEEE Access · doi:10.1109/access.2019.2918221 · Cited by 167
“It can obtain a better performance than Inception-v3 with the same parameters [24].”
MethodKandel, I., & Castelli, M. (2020) · Applied Sciences · doi:10.3390/app10062021 · Cited by 160
Non-Local Graph Neural Networks
Liu, M., Wang, Z., & Ji, S. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3134200 · Cited by 241
YOLO-ACN: Focusing on Small Target and Occluded Object Detection
Li, Y., Li, S., Du, H., Chen, L., Zhang, D., & Li, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3046515 · Cited by 166
“In addition, depthwise separable convolution [27], [28] is adopted instead of standard convolution, and leaky ReLU [29] is replaced with hard-swish [30] to reduce the parameters.”
A review of deep learning algorithms for computer vision systems in livestock
Borges Oliveira, D. A., Ribeiro Pereira, L. G., Bresolin, T., Pontes Ferreira, R. E., & Reboucas Dorea, J. R. (2021) · Livestock Science · doi:10.1016/j.livsci.2021.104700 · Cited by 163
“For example, xCeption (Chollet, 2016) and Mask R-CNN (He et al., 2017) were published in 2016 and 2017, respectively.”
Deep convolutional neural network models for weed detection in polyhouse grown bell peppers
Subeesh, A., Bhole, S., Singh, K., Chandel, N. S., Rajwade, Y. A., Rao, K. V. R., Kumar, S. P., & Jat, D. (2022) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2022.01.002 · Cited by 166
Review of Lightweight Deep Convolutional Neural Networks
Chen, F., Li, S., Han, J., Ren, F., & Yang, Z. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-10032-z · Cited by 164
“The Inception series started from GoogLeNet has made continuous progress in improving accuracy and decreasing the computational complexity of the network [25–28].”
Kunduracioglu, I., & Pacal, I. (2024) · Journal of Plant Diseases and Protection · doi:10.1007/s41348-024-00896-z · Cited by 166
$L1$ -Norm Batch Normalization for Efficient Training of Deep Neural Networks
Wu, S., Li, G., Deng, L., Liu, L., Wu, D., Xie, Y., & Shi, L. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876179 · Cited by 166
“field of convolutional neural networks (CNNs), there is a trend toward replacing the standard convolution with bottleneck pointwise convolution [26], group convolution [27], or depthwise convolution [28].”
BackgroundBlended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction
Bodapati, J. D., Naralasetti, V., Shareef, S. N., Hakak, S., Bilal, M., Maddikunta, P. K. R., & Jo, O. (2020) · Electronics · doi:10.3390/electronics9060914 · Cited by 163
Lei, L., Chen, T., Li, S., & Li, J. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00173 · Cited by 197
Kujur, A., Raza, Z., Khan, A. A., & Wechtaisong, C. (2022) · IEEE Access · doi:10.1109/access.2022.3216393 · Cited by 166
“This is achieved by comparing the classification performance of rigorous experimentation on four CNN variants namely S-CNN (trained from scratch) [12], ResNet50 [13], InceptionV3 [14], and Xception [15] and all four CNN models were compared with proposed PCA-CNN”
MethodInfluentialNaive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
Chen, L.-C., Lopes, R. G., Cheng, B., Collins, M. D., Cubuk, E. D., Zoph, B., Adam, H., & Shlens, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58545-7_40 · Cited by 165
“001 for Xception-71 (X-71) backbone [16,63] and 0.”
MethodHolistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer
Lin, S., Ji, R., Chen, C., Tao, D., & Luo, J. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2873305 · Cited by 164
“Recently, MobileNet [43] and Xception [44] have used the depthwise separable convolutions to achieve impressive performance among lightweight models.”
MethodLi, Y., Zhou, Y., Zhang, Y., Zhong, L., Wang, J., & Chen, J. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.02.013 · Cited by 162
A Machine Learning-Oriented Survey on Tiny Machine Learning
Capogrosso, L., Cunico, F., Cheng, D. S., Fummi, F., & Cristani, M. (2024) · IEEE Access · doi:10.1109/access.2024.3365349 · Cited by 255
Safonova, A., Tabik, S., Alcaraz-Segura, D., Rubtsov, A., Maglinets, Y., & Herrera, F. (2019) · Remote Sensing · doi:10.3390/rs11060643 · Cited by 164
“Xception was implemented in Keras by François Chollet and it is a modification of the Inception network (Chollet [41]).”
MethodCao, X., Jia, J., & Gong, N. Z. (2021) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3433210.3437526 · Cited by 272
“Overall, we consider Xception [5], VGG16 [30], ResNet152 [12], ResNet152V2 [13], ResNeXt101 [36], InceptionV3 [32], InceptionResNetV2 [31], MobileNet( α =1.0) [14], MobileNetV2( α =1.4)[ 29],DenseNet201[17],andNASNetLarge[40].”
InfluentialDeep learning for unmanned aerial vehicles detection: A review
Al-Qubaydhi, N., Alenezi, A., Alanazi, T., Senyor, A., Alanezi, N., Alotaibi, B., Alotaibi, M., Razaque, A., & Hariri, S. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2023.100614 · Cited by 206
Mahmood, H., Shaban, M., Indave, B. I., Santos-Silva, A. R., Rajpoot, N., & Khurram, S. A. (2020) · Oral Oncology · doi:10.1016/j.oraloncology.2020.104885 · Cited by 161
Synthetic Data Generation for Steel Defect Detection and Classification Using Deep Learning
Boikov, A., Payor, V., Savelev, R., & Kolesnikov, A. (2021) · Symmetry · doi:10.3390/sym13071176 · Cited by 159
GoogLeNet based on residual network and attention mechanism identification of rice leaf diseases
Yang, L., Yu, X., Zhang, S., Long, H., Zhang, H., Xu, S., & Liao, Y. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107543 · Cited by 162
DLMC-Net: Deeper lightweight multi-class classification model for plant leaf disease detection
Sharma, V., Tripathi, A. K., & Mittal, H. (2023) · Ecological Informatics · doi:10.1016/j.ecoinf.2023.102025 · Cited by 159
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
Zhuang, B., Shen, C., Tan, M., Liu, L., & Reid, I. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00050 · Cited by 158
“solve this problem, many existing works focus on network pruning [18,28,54], low-bit quantization [24,53] and/or efficient architecture design [8, 21].”
BackgroundMethodAlonso, I., Riazuelo, L., Montesano, L., & Murillo, A. C. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3007440 · Cited by 162
A review on computer vision systems in monitoring of poultry: A welfare perspective
Okinda, C., Nyalala, I., Korohou, T., Okinda, C., Wang, J., Achieng, T., Wamalwa, P., Mang, T., & Shen, M. (2020) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2020.09.002 · Cited by 158
An approach for multiclass skin lesion classification based on ensemble learning
Rahman, Z., Hossain, M. S., Islam, M. R., Hasan, M. M., & Hridhee, R. A. (2021) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2021.100659 · Cited by 160
Pacal, I. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122099 · Cited by 161
ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
He, Y., Gan, B., Chen, S., Zhou, Y., Yin, G., Song, L., Sheng, L., Shao, J., & Liu, Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00434 · Cited by 161
“• ELA-Xception and SNRFilters-Xception differ from Xception in the fact that they do not directly take RGB images as input.”
InfluentialWang, Y., Yu, K., Chen, C., Hu, X., & Peng, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00703 · Cited by 161
“Method +GaussianNoise +SaltPepperNoise +GaussianBlur ΔAcc(FF) ΔAcc(Wild) ΔAcc(FF) ΔAcc(Wild) ΔAcc(FF) ΔAcc(Wild) Xception [4] -2.”
BackgroundMobile Video Object Detection with Temporally-Aware Feature Maps
Zhu, M., & Liu, M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00596 · Cited by 160
Xue, D., Zhou, X., Li, C., Yao, Y., Rahaman, M. M., Zhang, J., Chen, H., Zhang, J., Qi, S., & Sun, H. (2020) · IEEE Access · doi:10.1109/access.2020.2999816 · Cited by 160
Flower species recognition system using convolution neural networks and transfer learning
Gogul, I., & Kumar, V. S. (2017) · International Conference on Signal Processing, Communication and Networking (ICSCN) · doi:10.1109/icscn.2017.8085675 · Cited by 191
Verhelst, M., & Moons, B. (2017) · IEEE Solid-State Circuits Magazine · doi:10.1109/mssc.2017.2745818 · Cited by 158
Customizable Architecture Search for Semantic Segmentation
Zhang, Y., Qiu, Z., Liu, J., Yao, T., Liu, D., & Mei, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01191 · Cited by 152
“The separable convolution proposed in [7] is an operation that efficiently balances cost and performance by factorizing the standard convolution into a depthwise convolution and a pointwise convolution.”
BackgroundHu, C., & Wang, Y. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2962437 · Cited by 159
“Duetotheefficiencyof depthwiseseparableconvolution[26],wereplaceentirestandard convolutions to the depthwise separable convolutions in residual blocks.”
BackgroundMethodPacal, I., Karaman, A., Karaboga, D., Akay, B., Basturk, A., Nalbantoglu, U., & Coskun, S. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.105031 · Cited by 159
Kumar, N., Sharma, M., Singh, V. P., Madan, C., & Mehandia, S. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103596 · Cited by 187
Jin, X., Yi, K., & Xu, J. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3180274 · Cited by 158
“Chollet [13] observe that the Inception family [14] can be improved by substituting Inception modules with stacks of depthwise separable convolutions and proposed the new network called Xception.”
BackgroundMicrostructure segmentation with deep learning encoders pre-trained on a large microscopy dataset
Stuckner, J., Harder, B. J., & Smith, T. M. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00878-5 · Cited by 205
Das, S., Imtiaz, M. S., Neom, N. H., Siddique, N., & Wang, H. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118914 · Cited by 158
A Comprehensive Overview and Comparative Analysis on Deep Learning Models
Perumal, T., Mustapha, N., Mohamed, R., & Shiri, F. M. (2024) · Journal on artificial intelligence · doi:10.32604/jai.2024.054314 · Cited by 676
Qi, K., Yang, H., Li, C., Liu, Z., Wang, M., Liu, Q., & Wang, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32248-9_28 · Cited by 184
“e long-range dependencies are eectively explored for brain stroke lesion segmentation. Considering the eectiveness of Depthwise Separable Convolution (DSC) in reducing convolution kernel parameters [13,14], this paper replaces the classical U-Net convolution operation with DSC. Moreover, a Feature Similarity Module (F…”
MethodSharma, P., Joshi, S., Gautam, S., Maharjan, S., Khanal, S. R., Reis, M. J. C. S., Barroso, J., & Filipe, V. M. D. J. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-22918-3_5 · Cited by 219
A Simple and Light-Weight Attention Module for Convolutional Neural Networks
Park, J., Woo, S., Lee, J.-Y., & Kweon, I. S. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01283-0 · Cited by 159
“MobileNet (Howard et al. 2017), sharing a similar philosophy with ResNeXt and Xception, use depth-wise convolutions with high cardinalities.”
MethodCOVID-19 detection from chest X-Ray images using Deep Learning and Convolutional Neural Networks
Makris, A., Kontopoulos, I., & Tserpes, K. (2020) · 11th Hellenic Conference on Artificial Intelligence · doi:10.1145/3411408.3411416 · Cited by 159
“Xception [16] replaced the Inception modules with depthwise separable convolutions.”
MethodChen, D., Lu, Y., Li, Z., & Young, S. N. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107091 · Cited by 210
FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation
Gao, G., Xu, G., Li, J., Yu, Y., Lu, H., & Yang, J. J. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3157995 · Cited by 169
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.