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 401–500 of 1,227
Zeineldin, R. A., Karar, M. E., Coburger, J., Wirtz, C. R., & Burgert, O. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02186-z · Cited by 226
“Then, other CNN models have dominated the ILSVRC competition; namely Visual Geometry Group Network (VGGNet) [15], Residual Neural Network (ResNet) [16], Dense Convolutional Network (DenseNet) [17], Xception [18], MobileNet [19], NASNet [20], and MobileNetV2 [21].”
BackgroundMethodModality specific U-Net variants for biomedical image segmentation: a survey
Punn, N. S., & Agarwal, S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10152-1 · Cited by 246
“The increased computations due to inception convolution in each module could be reduced by using depthwise separable convolutions (Chollet, 2017).”
BackgroundA cucumber leaf disease severity classification method based on the fusion of DeepLabV3+ and U-Net
Wang, C., Du, P., Wu, H., Li, J., Zhao, C., & Zhu, H. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106373 · Cited by 247
Deep Neural Networks for Medical Image Segmentation
Malhotra, P., Gupta, S., Koundal, D., Zaguia, A., & Enbeyle, W. (2022) · Journal of Healthcare Engineering · doi:10.1155/2022/9580991 · Cited by 248
“Different CNN models have been reported in the literature, including AlexNet [54], GoogleNet [55], VGG [56], Inception[57], SequeezeNet [58], and DenseNet [59].”
MethodRetractedMulti-fiber Networks for Video Recognition
Chen, Y., Kalantidis, Y., Li, J., Yan, S., & Feng, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_22 · Cited by 229
A generalized deep learning framework for whole-slide image segmentation and analysis
Khened, M., Kori, A., Rajkumar, H., Krishnamurthi, G., & Srinivasan, B. (2021) · Scientific Reports · doi:10.1038/s41598-021-90444-8 · Cited by 239
“, 2018) with Xception (Chollet, 2017) network as the backbone and pre-trained on”
BackgroundArtificial intelligence for aging and longevity research: Recent advances and perspectives
Zhavoronkov, A., Mamoshina, P., Vanhaelen, Q., Scheibye-Knudsen, M., Moskalev, A., & Aliper, A. (2019) · Ageing Research Reviews · doi:10.1016/j.arr.2018.11.003 · Cited by 246
“The model is based on a modified version of Xception (Chollet, 2017), a DNN-based model where all layers, except the last fully-connected layer are initialized with pre-trained weights from the ImageNet database.”
Low-Light Image Enhancement with Wavelet-Based Diffusion Models
Jiang, H., Luo, A., Fan, H., Han, S., & Liu, S. (2023) · ACM Transactions on Graphics · doi:10.1145/3618373 · Cited by 246
EfficientPS: Efficient Panoptic Segmentation
Mohan, R., & Valada, A. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01445-z · Cited by 238
Video to Events: Recycling Video Datasets for Event Cameras
Gehrig, D., Gehrig, M., Hidalgo-Carrio, J., & Scaramuzza, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00364 · Cited by 236
“We use the network architecture proposed in [1] which consists of a U-Net architecture [35] with an Xception encoder [8] and a light decoder architecture.”
MethodResource Efficient 3D Convolutional Neural Networks
Kopuklu, O., Kose, N., Gunduz, A., & Rigoll, G. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00240 · Cited by 245
“Depthwise separable convolutions are introduced in Xception [5] and they are the main building blocks for majority of lightweight architectures.”
BackgroundChen, H., Li, C., Wang, G., Li, X., Mamunur Rahaman, M., Sun, H., Hu, W., Li, Y., Liu, W., Sun, C., et al. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108827 · Cited by 240
Triplet Fingerprinting: More Practical and Portable Website Fingerprinting with N-shot Learning
Sirinam, P., Mathews, N., Rahman, M. S., & Wright, M. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3354217 · Cited by 231
“We test with the DF model, as well as using techniques from Sriniam et al. [29] to adapt previously-proposed DL models used in image recognition, namely GoogleNet [31], RestNet [12] and Xception [8], for the WF problem.”
BackgroundMethodA deep learning based image enhancement approach for autonomous driving at night
Li, G., Yang, Y., Qu, X., Cao, D., & Li, K. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106617 · Cited by 242
CrackW-Net: A Novel Pavement Crack Image Segmentation Convolutional Neural Network
Han, C., Ma, T., Huyan, J., Huang, X., & Zhang, Y. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3095507 · Cited by 241
End-Edge-Cloud Collaborative Computing for Deep Learning: A Comprehensive Survey
Wang, Y., Yang, C., Lan, S., Zhu, L., & Zhang, Y. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3393230 · Cited by 237
Haase, D., & Amthor, M. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01461 · Cited by 220
Hossain, S., Chakrabarty, A., Gadekallu, T. R., Alazab, M., & Piran, M. J. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3266614 · Cited by 239
“InceptionV3 is more efficient than its predecessors v 1 and v 2 , is computationally less expensive, and uses auxiliary classifiers as regularizers [43].”
BackgroundNeural Image Compression for Gigapixel Histopathology Image Analysis
Tellez, D., Litjens, G., van der Laak, J., & Ciompi, F. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2936841 · Cited by 242
“In particular, all convolutional layers were set to use depthwise separable convolutions, a type of convolution that reduces the number of parameters while maintaining a similar level of performance [29].”
MethodConv2Former: A Simple Transformer-Style ConvNet for Visual Recognition
Hou, Q., Lu, C.-Z., Cheng, M.-M., & Feng, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3401450 · Cited by 239
PD2SE-Net: Computer-assisted plant disease diagnosis and severity estimation network
Liang, Q., Xiang, S., Hu, Y., Coppola, G., Zhang, D., & Sun, W. (2019) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2019.01.034 · Cited by 238
A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D Images
Ulku, I., & Akagündüz, E. (2022) · Applied Artificial Intelligence · doi:10.1080/08839514.2022.2032924 · Cited by 237
“…information in real-time applications including attention mechanisms (Ding et al. 2021; Hu et al. 2020), depth-wise separable convolutions (Chollet 2017; Howard et al. 2019), pyramid fusion (Rosas-Arias et al. 2021; Orši´c and Šegvi´c 2021), grouped convolutions (Zhang et al. 2018; Huang…”
BackgroundShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ma, N., Zhang, X., Zheng, H.-T., & Sun, J. (2018) · arXiv · Cited by 7,344
“Recent advances in light-weight neural network architectures [2,8,18,21,24, 35,39] are mostly based on the metric of FLOPs and do not consider these properties above.”
BackgroundMethodInfluentialTransfer Learning with ResNet-50 for Malaria Cell-Image Classification
Reddy, A. S. B., & Juliet, D. S. (2019) · 2019 International Conference on Communication and Signal Processing (ICCSP) · doi:10.1109/iccsp.2019.8697909 · Cited by 238
ResGANet: Residual group attention network for medical image classification and segmentation
Cheng, J., Tian, S., Yu, L., Gao, C., Kang, X., Ma, X., Wu, W., Liu, S., & Lu, H. (2022) · Medical Image Analysis · doi:10.1016/j.media.2021.102313 · Cited by 237
Convolutional Neural Networks in Detection of Plant Leaf Diseases: A Review
Tugrul, B., Elfatimi, E., & Eryigit, R. (2022) · Agriculture · doi:10.3390/agriculture12081192 · Cited by 234
“Keras [25] Python Windows, Linux, macOS Yes Yes”
MethodHDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
Hu, X., Cai, Y., Lin, J., Wang, H., Yuan, X., Zhang, Y., Timofte, R., & Van Gool, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01702 · Cited by 215
“2, we replace the standard convolution with the depthwise-separable convolution (DSC) [4, 8, 31] to reduce the computational cost.”
MethodDeepRx: Fully Convolutional Deep Learning Receiver
Honkala, M., Korpi, D., & Huttunen, J. M. J. (2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3054520 · Cited by 234
“We also observed improved results when using depthwise separable convolutions [28], [29] instead of normal convolutions.”
Gupta, A., Anjum, Gupta, S., & Katarya, R. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106859 · Cited by 236
“Xception [8] stands for ‘‘extreme inception’’.”
Westphal, E., & Seitz, H. (2021) · Additive Manufacturing · doi:10.1016/j.addma.2021.101965 · Cited by 233
Multiple Feature Reweight DenseNet for Image Classification
Zhang, K., Guo, Y., Wang, X., Yuan, J., & Ding, Q. (2019) · IEEE Access · doi:10.1109/access.2018.2890127 · Cited by 234
“GoogleNets [12], [16]–[19] used multiple scale convolution kernels on a single-layer convolutional layer to enhance the feature extraction capabilities.”
MethodLightweight Underwater Object Detection Based on YOLO v4 and Multi-Scale Attentional Feature Fusion
Zhang, M., Xu, S., Song, W., He, Q., & Wei, Q. (2021) · Remote Sensing · doi:10.3390/rs13224706 · Cited by 234
“The former, such as SqueezeNet, MobileNet (V1, V2) [14,15], ShuffleNet [21], Xception [31], etc., aims to design different convolutional methods and structures to make convolution neural networks more lightweight.”
MethodDetecting Deep-Fake Videos from Phoneme-Viseme Mismatches
Agarwal, S., Farid, H., Fried, O., & Agrawala, M. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00338 · Cited by 234
Dung, C. V., Sekiya, H., Hirano, S., Okatani, T., & Miki, C. (2019) · Automation in Construction · doi:10.1016/j.autcon.2019.02.013 · Cited by 233
COVID-19 image classification using deep features and fractional-order marine predators algorithm
Sahlol, A. T., Yousri, D., Ewees, A. A., Al-qaness, M. A. A., Damasevicius, R., & Elaziz, M. A. (2020) · Scientific Reports · doi:10.1038/s41598-020-71294-2 · Cited by 234
Hosseinpour, H., Samadzadegan, F., & Javan, F. D. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.12.007 · Cited by 227
“This work proposes a residual depth-wise separable convolutional (R-DSC) module, which is based on residual connection unit (RCU) (He et al., 2016) and depth-wise separable convolutional (DSC) operation (Chollet, 2016) for the decoder section of the CMGFNet.”
Transfer learning for medical images analyses: A survey
Yu, X., Wang, J., Hong, Q.-Q., Teku, R., Wang, S.-H., & Zhang, Y.-D. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.08.159 · Cited by 232
Knowledge Adaptation for Efficient Semantic Segmentation
He, T., Shen, C., Tian, Z., Gong, D., Sun, C., & Yan, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00067 · Cited by 223
“To demonstrate the effectiveness of our method, we select two totally different teacher models, ResNet-50 [10] and Xception-41 [6].”
BackgroundMethodInfluentialRTNet: Relation Transformer Network for Diabetic Retinopathy Multi-Lesion Segmentation
Huang, S., Li, J., Xiao, Y., Shen, N., & Xu, T. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3143833 · Cited by 230
“ResNet-34 [43], ResNet-50 [43], Xcep-tion [44], Vgg19-bn [7] and DenseNet-161 [41] integrated with UNet are implemented with the segmentation heads of our network.”
MethodInfluentialDiabetic Retinopathy Classification Using a Modified Xception Architecture
Kassani, S. H., Kassani, P. H., Khazaeinezhad, R., Wesolowski, M. J., Schneider, K. A., & Deters, R. (2019) · 2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) · doi:10.1109/isspit47144.2019.9001846 · Cited by 209
“• Xception: The Xception architecture [17], introduced by Francois Chollet, is an extension of the Inception architecture.”
BackgroundDeep learning-based predictive identification of neural stem cell differentiation
Zhu, Y., Huang, R., Wu, Z., Song, S., Cheng, L., & Zhu, R. (2021) · Nature Communications · doi:10.1038/s41467-021-22758-0 · Cited by 230
Timeception for Complex Action Recognition
Hussein, N., Gavves, E., & Smeulders, A. W. M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00034 · Cited by 225
“Xception [43] argues that separable 2D convolutions are as effective as typical 2D convolutions.”
BackgroundMethodKyrkou, C., & Theocharides, T. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2969809 · Cited by 226
“FireNet [35], MobileNets [21]–[23], Xception [19], ShuffleNet [25],EfficientNet [26], and SqueezeNet [24].”
BackgroundMethodBrain Tumor Classification Using Deep Learning
Saleh, A., Sukaik, R., & Abu-Naser, S. S. (2020) · 2020 International Conference on Assistive and Rehabilitation Technologies (iCareTech) · doi:10.1109/icaretech49914.2020.00032 · Cited by 210
Hashimoto, N., Fukushima, D., Koga, R., Takagi, Y., Ko, K., Kohno, K., Nakaguro, M., Nakamura, S., Hontani, H., & Takeuchi, I. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00391 · Cited by 227
“Feature extractor G f : x 7→ h is a CNN which maps a 224 × 224 -pixel image x into a Q -dimensional feature vector h .”
BackgroundInfluentialRecycleNet: Intelligent Waste Sorting Using Deep Neural Networks
Bircanoglu, C., Atay, M., Beser, F., Genc, O., & Kizrak, M. A. (2018) · 2018 Innovations in Intelligent Systems and Applications (INISTA) · doi:10.1109/inista.2018.8466276 · Cited by 224
Soft Labels for Ordinal Regression
Díaz, R., & Marathe, A. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00487 · Cited by 217
Methods for Pruning Deep Neural Networks
Vadera, S., & Ameen, S. (2022) · IEEE Access · doi:10.1109/access.2022.3182659 · Cited by 223
Recurrent convolutional structures for audio spoof and video deepfake detection
Chintha, A., Thai, B., Sohrawardi, S. J., Bhatt, K., Hickerson, A., Wright, M., & Ptucha, R. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2999185 · Cited by 226
“Our architecture for deepfake detection is inspired by the XceptionNet [32] architecture along with recurrent processing used in ConvLSTM [20] and FaceNetLSTM [33].”
BackgroundMethodInfluential(2023) · doi:10.1109/cvpr52729.2023.01808 · Cited by 226
“D depth-wise convolution layer [10] over temporal di-mension with window size w .”
BackgroundMethodA Novel Intrusion Detection Method Based on Lightweight Neural Network for Internet of Things
Zhao, R., Gui, G., Xue, Z., Yin, J., Ohtsuki, T., Adebisi, B., & Gacanin, H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3119055 · Cited by 224
Tan, C., Liu, H., Zhao, Y., Wei, S., Gu, G., Liu, P., & Wei, Y. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02657 · Cited by 225
Kusunose, K., Abe, T., Haga, A., Fukuda, D., Yamada, H., Harada, M., & Sata, M. (2020) · JACC: Cardiovascular Imaging · doi:10.1016/j.jcmg.2019.02.024 · Cited by 223
Improved Residual Networks for Image and Video Recognition
Duta, I. C., Liu, L., Zhu, F., & Shao, L. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9412193 · Cited by 210
A Survey of Data-driven and Knowledge-aware eXplainable AI
Li, X.-H., Cao, C. C., Shi, Y., Bai, W., Gao, H., Qiu, L., Wang, C., Gao, Y., Zhang, S., Xue, X., et al. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2983930 · Cited by 224
Mini-YOLOv3: Real-Time Object Detector for Embedded Applications
Mao, Q.-C., Sun, H.-M., Liu, Y.-B., & Jia, R.-S. (2019) · IEEE Access · doi:10.1109/access.2019.2941547 · Cited by 224
“First, we define the unit of the network: We changed the standard convolution to depthwise separable convolutions according to Google ‘‘Xception’’ [33].”
MethodPham, H. H., Le, T. T., Tran, D. Q., Ngo, D. T., & Nguyen, H. Q. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.03.127 · Cited by 214
Capra, M., Bussolino, B., Marchisio, A., Masera, G., Martina, M., & Shafique, M. (2020) · IEEE Access · doi:10.1109/access.2020.3039858 · Cited by 222
“Xception [212] adopts this same approach.”
ID-Reveal: Identity-aware DeepFake Video Detection
Cozzolino, D., Rossler, A., Thies, J., Niesner, M., & Verdoliva, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01483 · Cited by 221
HOG-ShipCLSNet: A Novel Deep Learning Network With HOG Feature Fusion for SAR Ship Classification
Zhang, T., Zhang, X., Ke, X., Liu, C., Xu, X., Zhan, X., Wang, C., Ahmad, I., Zhou, Y., Pan, D., et al. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3082759 · Cited by 211
Asif, S., Yi, W., Ain, Q. U., Hou, J., Yi, T., & Si, J. (2022) · IEEE Access · doi:10.1109/access.2022.3153306 · Cited by 217
Comparison of CNN-based deep learning architectures for rice diseases classification
Ahad, M. T., Li, Y., Song, B., & Bhuiyan, T. (2023) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2023.07.001 · Cited by 218
DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
Qi, H., Guo, Q., Juefei-Xu, F., Xie, X., Ma, L., Feng, W., Liu, Y., & Zhao, J. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413707 · Cited by 220
“pFakes by monitoring the heartbeat rhythms. More specifically, DeepRhythm outperforms four state-of-the-art DeepFake detection methods including Bayer’s method [3], Inception ResNet V1 [59], Xception [9], and MesoNet [1] in the FaceForensics++ benchmark [57] and exhibits high robustness to JPEG compression, noise, and…”
BackgroundMethodInfluentialImplicit identity leakage: The stumbling block to improving deepfake detection generalization
Dong, S., Wang, J., Ji, R., Liang, J., Fan, H., & Ge, Z. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00389 · Cited by 220
“To be specific, we froze the input feature to the last linear layer of ResNet-18/34/50 [28], Xception [13] and Efficient-b3 [75] to demonstrate the universality of such phenomenon.”
MethodInfluentialCLIP-Q: Deep Network Compression Learning by In-parallel Pruning-Quantization
Tung, F., & Mori, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00821 · Cited by 220
“Xception [4] replaces Inception modules [48] with depth-wise separable convolutions.”
BackgroundSpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
Du, X., Lin, T.-Y., Jin, P., Ghiasi, G., Tan, M., Cui, Y., Le, Q. V., & Song, X. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01161 · Cited by 212
Santamaría-Vázquez, E., Martínez-Cagigal, V., Vaquerizo-Villar, F., & Hornero, R. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3048106 · Cited by 213
“Depthwise convolutions were first used in the image classification domain to factorize a convolution kernel into smaller kernels by acting on each input channel separately, reducing the total amount of parameters [17], [37].”
MethodAutomated pixel-level pavement distress detection based on stereo vision and deep learning
Guan, J., Yang, X., Ding, L., Cheng, X., Lee, V. C. S., & Jin, C. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.103788 · Cited by 216
Shorfuzzaman, M., & Hossain, M. S. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2020.107700 · Cited by 217
“A comparison of performance results is also done with different pre-trained CNN models such as Inception [36] , Xception [37] , Inception ResNet v2 [36] , VGG-16 [8] .”
Joint Audio-Visual Deepfake Detection
Zhou, Y., & Lim, S.-N. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01453 · Cited by 217
Fingerprint Spoof Buster: Use of Minutiae-Centered Patches
Chugh, T., Cao, K., & Jain, A. K. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2812193 · Cited by 216
Dual Cross-Attention for medical image segmentation
Ates, G. C., Mohan, P., & Celik, E. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107139 · Cited by 215
“Then, we replace the linear projections in both channel and spatial attention modules with depth-wise convolutions [9].”
MethodExplainable COVID-19 Detection Using Chest CT Scans and Deep Learning
Alshazly, H., Linse, C., Barth, E., & Martinetz, T. (2021) · Sensors · doi:10.3390/s21020455 · Cited by 216
Zhang, D., Yao, L., Zhang, X., Wang, S., Chen, W., Boots, R., & Benatallah, B. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11496 · Cited by 210
Detection of Apple Plant Diseases Using Leaf Images Through Convolutional Neural Network
Vishnoi, V. K., Kumar, K., Kumar, B., Mohan, S., & Khan, A. A. (2023) · IEEE Access · doi:10.1109/access.2022.3232917 · Cited by 214
“Comparison With Other Methods: The performance of the model is contrasted with pre-trained models including VGG-19 [9], ResNet-152 [10], DenseNet-201 [11], MobileNetV2 [12], ResNet-50 [10], VGG-16 [9], Incep-tionV3 [13], Xception [14], and MobileNet [15] using transfer learning approach.”
MethodResultAutomatic Lung Cancer Prediction from Chest X-ray Images Using the Deep Learning Approach
Ausawalaithong, W., Thirach, A., Marukatat, S., & Wilaiprasitporn, T. (2018) · 2018 11th Biomedical Engineering International Conference (BMEiCON) · doi:10.1109/bmeicon.2018.8609997 · Cited by 168
SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
Gao, N., Shan, Y., Wang, Y., Zhao, X., Yu, Y., Yang, M., & Huang, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00073 · Cited by 204
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Wu, H., Zhang, J., Huang, K., Liang, K., & Yu, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11816 · Cited by 214
“Four separable convolutions [14, 9] the convolution with dilation rate 1 is employed to capture the relation between y 0 m and the rest part of y m , as shown by the blue box in Figure 5.”
MethodClassification of TrashNet Dataset Based on Deep Learning Models
Aral, R. A., Keskin, S. R., Kaya, M., & Haciomeroglu, M. (2018) · 2018 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2018.8622212 · Cited by 214
“Briefly, this architecture is very easy to describe and change because it is a linear heap of depthwise separable convolution layers with residual relations [13].”
BackgroundIqbal, S., N. Qureshi, A., Li, J., & Mahmood, T. (2023) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09899-9 · Cited by 210
“The 1x1 convolution used to adjust the scale via pointwise convolution [102].”
BackgroundMethodCountry-wide high-resolution vegetation height mapping with Sentinel-2
Lang, N., Schindler, K., & Wegner, J. D. (2019) · Remote Sensing of Environment · doi:10.1016/j.rse.2019.111347 · Cited by 202
Taylor, A. G., Mielke, C., & Mongan, J. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002697 · Cited by 212
Vehicle Re-Identification With Viewpoint-Aware Metric Learning
Chu, R., Sun, Y., Li, Y., Liu, Z., Zhang, C., & Wei, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00837 · Cited by 203
“We recommend using the Xception-based predictor with consideration of computational efficiency.”
MethodInfluentialEffective Feature Fusion Network in BIFPN for Small Object Detection
Chen, J., Mai, H., Luo, L., Chen, X., & Wu, K. (2021) · 2021 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip42928.2021.9506347 · Cited by 193
“…feature of the third layer, P td 4 matches the resolution with the P 3 layer through deconvolution, and P out 3 is activated by the Swish[17] activation function after fusion, and we use depthwise separable convolution[18] for feature fusion, and adds batch normalization after each convolution.”
MethodMirzaei, G., & Adeli, H. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103293 · Cited by 211
AgriDet: Plant Leaf Disease severity classification using agriculture detection framework
Pal, A., & Kumar, V. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105754 · Cited by 206
Mahmood, T., Arsalan, M., Owais, M., Lee, M. B., & Park, K. R. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9030749 · Cited by 209
“Xception network [32] was used for the reduction of false positives.”
MethodDual Contrastive Learning for General Face Forgery Detection
Sun, K., Yao, T., Chen, S., Ding, S., Li, J., & Ji, R. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20130 · Cited by 209
“We compare DCL with several recently state-of-the-art methods, including Xception (Chollet 2017), EfficientNet-b4 (Tan and Le 2019), Face Xray (Tan and Le 2019), MLDG (Li et al.”
MethodDeep Dual-Channel Neural Network for Image-Based Smoke Detection
Gu, K., Xia, Z., Qiao, J., & Lin, W. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2929009 · Cited by 209
“For example, some typical networks, such as Alex-Net [11], ZF-Net [12], VGG-Net [13], GoogLe-Net [14], Xception [15], and Res-Net [16], illustrate that neural networks”
BackgroundPixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
Zhong, Y., Yuan, B., Wu, H., Yuan, Z., Peng, J., & Wang, Y.-X. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00718 · Cited by 196
Liu, W., Li, C., Xu, N., Jiang, T., Rahaman, M. M., Sun, H., Wu, X., Hu, W., Chen, H., Sun, C., et al. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108829 · Cited by 206
“This method separates spatial convolution and channel convolution [11].”
MethodInfluentialAn efficient deep learning model to categorize brain tumor using reconstruction and fine-tuning
Talukder, M. A., Islam, M. M., Uddin, M. A., Akhter, A., Pramanik, M. A. J., Aryal, S., Almoyad, M. A. A., Hasan, K. F., & Moni, M. A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120534 · Cited by 205
Aziz, L., Haji Salam, M. S. B., Sheikh, U. U., & Ayub, S. (2020) · IEEE Access · doi:10.1109/access.2020.3021508 · Cited by 204
“Recently, He et al. [65] proposed a block called Squeeze and Excitation( SE) blocks, which enhance the performance of existing deep architecture at minimal additional computational cost, adaptively recalibrating channel-wise such as Hourglass [127], Dilated Residual Networks [137], Xception [138], DetNet [139], Dual P…”
BackgroundHuang, L., Luo, J., Lin, Z., Niu, F., & Liu, L. (2020) · Remote Sensing of Environment · doi:10.1016/j.rse.2019.111534 · Cited by 203
SoyNet: Soybean leaf diseases classification
Karlekar, A., & Seal, A. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105342 · Cited by 203
Ayan, E., Erbay, H., & Varçın, F. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105809 · Cited by 206
Garbage classification system based on improved ShuffleNet v2
Chen, Z., Yang, J., Chen, L., & Jiao, H. (2022) · Resources, Conservation and Recycling · doi:10.1016/j.resconrec.2021.106090 · Cited by 204
Measuring Robustness to Natural Distribution Shifts in Image Classification
Taori, R., Dave, A., Shankar, V., Carlini, N., Recht, B., & Schmidt, L. (2020) · arXiv · doi:10.48550/arxiv.2007.00644 · Cited by 206
CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images
Zhou, Y., Graham, S., Alemi Koohbanani, N., Shaban, M., Heng, P.-A., & Rajpoot, N. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00050 · Cited by 225
“G [42] 89.96 ± 3.54 ResNet50 [26] 92.08 ± 2.08 MobileNet [27] 92.78 ± 2.74 InceptionV3 [46] 91.37 ± 3.55 Xception [8] 92.09 ± 0.98 CA-CNN [41] 95.70 ± 3.04 Ours 97.00 ± 1.10”
MethodInfluentialSemantic Stereo for Incidental Satellite Images
Bosch, M., Foster, K., Christie, G., Wang, S., Hager, G. D., & Brown, M. (2019) · 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2019.00167 · Cited by 189
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.