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 301–400 of 1,227
A Review of Deep Learning on Medical Image Analysis
Wang, J., Zhu, H., Wang, S.-H., & Zhang, Y.-D. (2021) · Mobile Networks and Applications · doi:10.1007/s11036-020-01672-7 · Cited by 303
Multiview Transformers for Video Recognition
Yan, S., Xiong, X., Arnab, A., Lu, Z., Zhang, M., Sun, C., & Schmid, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00333 · Cited by 312
“Since AlexNet [36] won the ImageNet challenge by a large margin, CNNs have been quickly adopted to various vision tasks, their architectures have been refined over many generations [12,27,58,64] and later improved by Neural Architecture Search (NAS) [54,66,86].”
DeepFake Detection Based on Discrepancies Between Faces and Their Context
Nirkin, Y., Wolf, L., Keller, Y., & Hassner, T. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3093446 · Cited by 312
“fakes detected by our method but undetected by the state of the art XceptionNet fake detector [60].”
BackgroundMethodInfluentialCombining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space LayersPreprint
Gu, A., Johnson, I., Goel, K., Saab, K. K., Dao, T., Rudra, A., & Ré, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.13985 · Cited by 1,050
Islam, M. N., Hasan, M., Hossain, M. K., Alam, M. G. R., Uddin, M. Z., & Soylu, A. (2022) · Scientific Reports · doi:10.1038/s41598-022-15634-4 · Cited by 306
Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images
Zhou, Y., He, X., Huang, L., Liu, L., Zhu, F., Cui, S., & Shao, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00218 · Cited by 285
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
Chen, L., Zhang, Y., Song, Y., Liu, L., & Wang, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01815 · Cited by 307
“To ensure fair comparisons, we use the provided codes of Xception [41], RFM [47], and SRM [30] from the authors, and we reimplement Face X-ray [24] and F3Net [39] rigorously following the companion paper’s instructions and train these models under the same settings.”
MethodInfluentialDeep fake image detection based on pairwise learning
Hsu, C.-C., Zhuang, Y.-X., & Lee, C.-Y. (2020) · Applied Sciences · doi:10.3390/app10010370 · Cited by 304
“Other advanced CNNs, such as DenseNet [19], ResNet [20], Xception [12], can also be applied to the fake face detector training.”
BackgroundMethodInfluentialVOLO: Vision Outlooker for Visual Recognition
Yuan, L., Hou, Q., Jiang, Z., Feng, J., & Yan, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3206108 · Cited by 288
Diabetic Retinopathy Fundus Image Classification and Lesions Localization System Using Deep Learning
Alyoubi, W. L., Abulkhair, M. F., & Shalash, W. M. (2021) · Sensors · doi:10.3390/s21113704 · Cited by 303
“Kassani et al. [33] modified Xception model [43] to classify the DR stages in the APTOS 2019 Kaggle dataset [46], resulting in a 83.09% ACC.”
BackgroundMethodInfluentialCAT: Cross Attention in Vision Transformer
Lin, H., Cheng, X., Wu, X., & Shen, D. (2022) · 2022 IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme52920.2022.9859720 · Cited by 269
Recent Advances in Crop Disease Detection Using UAV and Deep Learning Techniques
Shahi, T. B., Xu, C.-Y., Neupane, A., & Guo, W. (2023) · Remote Sensing · doi:10.3390/rs15092450 · Cited by 295
Rahaman, M. M., Li, C., Yao, Y., Kulwa, F., Rahman, M. A., Wang, Q., Qi, S., Kong, F., Zhu, X., & Zhao, X. (2020) · Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics · doi:10.3233/xst-200715 · Cited by 302
Wani, J. A., Sharma, S., Muzamil, M., Ahmed, S., Sharma, S., & Singh, S. (2022) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-021-09588-5 · Cited by 301
Deep learning in multi-object detection and tracking: state of the art
Pal, S. K., Pramanik, A., Maiti, J., & Mitra, P. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02293-7 · Cited by 298
“To achieve better accuracy and efficiency, researchers can choose deeper and denser backbones, such as ResNet [55], ResNetXt [56], and AmoebaNet [57], or lightweight backbones, such as MobileNet [58], SqueezeNet [59], Xception [60], and MobileNetV2 [61].”
BackgroundContrastive Learning of Subject-Invariant EEG Representations for Cross-Subject Emotion Recognition
Shen, X., Liu, X., Hu, X., Zhang, D., & Song, S. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3164516 · Cited by 296
Eff-UNet: A Novel Architecture for Semantic Segmentation in Unstructured Environment
Baheti, B., Innani, S., Gajre, S., & Talbar, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00187 · Cited by 278
“Since 2012, various Convolutional Neural Network based architectures like VGG16 [25], ResNet [11], MobileNet [12], Xception [9], and recently introduced EfficientNet [28] have been evolving and have established benchmarks in image classification.”
BackgroundSelf-Training Multi-Sequence Learning with Transformer for Weakly Supervised Video Anomaly Detection
Li, S., Liu, F., & Jiao, L. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20028 · Cited by 280
“In order to achieve our MSL, we propose a Transformer-based Multi-Sequence Learning Network, which includes a multi-layer Convolutional Transformer En-coder to encode extracted snippet features, a Video Classifier to predict video-level anomaly scores, and a Snippet Regres-sor to predict snippet-level anomaly scores.”
MethodInfluentialDeepFake Detection for Human Face Images and Videos: A Survey
Malik, A., Kuribayashi, M., Abdullahi, S. M., & Khan, A. N. (2022) · IEEE Access · doi:10.1109/access.2022.3151186 · Cited by 297
“Jeon et al. [73] introduced an FDFtNet method to improve the capability of existing CNN models, such as SqueezeNet, ShallowNetV3, ResNetV2, and Xception.”
MethodInfluentialOil Spill Identification from Satellite Images Using Deep Neural Networks
Krestenitis, M., Orfanidis, G., Ioannidis, K., Avgerinakis, K., Vrochidis, S., & Kompatsiaris, I. (2019) · Remote Sensing · doi:10.3390/rs11151762 · Cited by 288
Single-Stage Semantic Segmentation From Image Labels
Araslanov, N., & Roth, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00431 · Cited by 275
Qin, B., & Li, D. (2020) · Sensors · doi:10.3390/s20185236 · Cited by 296
“To illustrate the advantages and reason for using MobileNet-v2 as the facemask-wearing condition identification network, comparisons with other CNNs, including Inception-v3 [80], DenseNet201 [41], ResNet50 [38], DarkNet19 [81], Xception [40], and VGG19 [36], in terms of network parameters and running time for a single…”
BackgroundMethodInfluentialDeep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective
Sarker, I. H. (2021) · doi:10.20944/preprints202102.0340.v1 · Cited by 295
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices
Qin, Z., Li, Z., Zhang, Z., Bao, Y., Yu, G., Peng, Y., & Sun, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00682 · Cited by 295
“Recent progress in lightweight image classification networks [3, 33, 20, 11, 28] has facilitated real-time object detection [11, 28, 14, 20] on GPU.”
BackgroundInfluentialDeep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective
Sarker, I. H. (2021) · SN Computer Science · doi:10.1007/s42979-021-00535-6 · Cited by 289
“Several advanced CNN-based deep learning models, such as AlexNet [69], Xception [70], Inception [71], visual geometry group (VGG) [72], ResNet [73], etc., or other lightweight architecture of the model can be used to minimize the issues depending on the problem domain and data characteristics.”
MethodRethinking Bottleneck Structure for Efficient Mobile Network Design
Zhou, D., Hou, Q., Chen, Y., Feng, J., & Yan, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58580-8_40 · Cited by 292
A Review on Deep Learning Techniques for the Diagnosis of Novel Coronavirus (COVID-19)
Islam, M. M., Karray, F., Alhajj, R., & Zeng, J. (2021) · IEEE Access · doi:10.1109/access.2021.3058537 · Cited by 292
“The pre-trained models which are used in the system are VGG19, MobileNetv2, Inception, Xception, and Inception-ResNetv2.”
MethodInfluentialEl Asnaoui, K., Chawki, Y., & Idri, A. (2021) · Studies in Big Data · doi:10.1007/978-3-030-74575-2_14 · Cited by 289
Han, W., Zhang, Z., Zhang, Y., Yu, J., Chiu, C.-C., Qin, J., Gulati, A., Pang, R., & Wu, Y. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-2059 · Cited by 287
Towards High Performance Video Object Detection
Zhu, X., Dai, J., Yuan, L., & Wei, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00753 · Cited by 285
Representative Forgery Mining for Fake Face Detection
Wang, C., & Deng, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01468 · Cited by 288
“The whole process can be divided into two steps: Firstly, following the training iteration in [11], we trained an Xception- based detector on the incomplete DFFD until the detector achieves the same TDR0.”
MethodInfluentialLiang, G., Hong, H., Xie, W., & Zheng, L. (2018) · IEEE Access · doi:10.1109/access.2018.2846685 · Cited by 284
“In this article, our pre-trained model is Xception [40], and we use the ReLU (Linear Rectification Function) as our activation function.”
MethodLoey, M., Manogaran, G., & Khalifa, N. E. M. (2025) · Neural Computing and Applications · doi:10.1007/s00521-020-05437-x · Cited by 286
“Many DTL models were introduced as AlexNet [22], VGGNet [30], GoogleNet [31], ResNet [32], Xception [33], DenseNet [34], Inception-V3 [35].”
MethodDelving deep into spatial pooling for squeeze-and-excitation networks
Jin, X., Xie, Y., Wei, X.-S., Zhao, B.-R., Chen, Z.-M., & Tan, X. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2021.108159 · Cited by 278
Wang, L., Li, R., Wang, D., Duan, C., Wang, T., & Meng, X. (2021) · Remote Sensing · doi:10.3390/rs13163065 · Cited by 281
A multi-class skin Cancer classification using deep convolutional neural networks
Chaturvedi, S. S., Tembhurne, J. V., & Diwan, T. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09388-2 · Cited by 283
“We performed extensive research in determining the best set-up of hyper-parameters for five models pre-trained on ImageNet [17] namely Xception [15], InceptionV3 [71], InceptionResNetV2 [70], NASNetLarge [83], and ResNetXt101 [77] and their ensembles InceptionV3 + Xception, InceptionResNetV2 +…”
MethodDetection and classification of soybean pests using deep learning with UAV images
Tetila, E. C., Machado, B. B., Astolfi, G., Belete, N. A. D. S., Amorim, W. P., Roel, A. R., & Pistori, H. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105836 · Cited by 283
Monkeypox Virus Detection Using Pre-trained Deep Learning-based Approaches
Sitaula, C., & Shahi, T. B. (2022) · Journal of Medical Systems · doi:10.1007/s10916-022-01868-2 · Cited by 282
CNN-Based Transformer Model for Fault Detection in Power System Networks
Thomas, J. B., Chaudhari, S. G., K. V., S., & Verma, N. K. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3238059 · Cited by 275
Fully automatic wound segmentation with deep convolutional neural networks
Wang, C., Anisuzzaman, D. M., Williamson, V., Dhar, M. K., Rostami, B., Niezgoda, J., Gopalakrishnan, S., & Yu, Z. (2020) · Scientific Reports · doi:10.1038/s41598-020-78799-w · Cited by 279
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
Xiong, Y., Li, Z., Chen, Y., Wang, F., Zhu, X., Luo, J., Wang, W., Lu, T., Li, H., Qiao, Y., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00540 · Cited by 268
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) · arXiv · doi:10.48550/arxiv.2006.07634 · Cited by 280
“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…”
BackgroundMethodInfluentialConvolutional Neural Network for Remote-Sensing Scene Classification: Transfer Learning Analysis
Pires de Lima, R., & Marfurt, K. (2019) · Remote Sensing · doi:10.3390/rs12010086 · Cited by 276
Jin, Z., Qiu, Y., Zhang, K., Li, H., & Luo, W. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3559891 · Cited by 266
“To further reduce the computational cost, we incorporate depthwise separable convolutions [48] in the model.”
Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
Kriman, S., Beliaev, S., Ginsburg, B., Huang, J., Kuchaiev, O., Lavrukhin, V., Leary, R., Li, J., & Zhang, Y. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053889 · Cited by 278
“Our approach is directly related to MobileNets [7, 8] and Xception [9], which uses depthwise separable convolutions [10, 11].”
MethodDO-Conv: Depthwise Over-Parameterized Convolutional Layer
Cao, J., Li, Y., Sun, M., Chen, Y., Lischinski, D., Cohen-Or, D., Chen, B., & Tu, C. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3175432 · Cited by 272
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
Yan, B., Peng, H., Wu, K., Wang, D., Fu, J., & Lu, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01493 · Cited by 277
Caries Detection with Near-Infrared Transillumination Using Deep Learning
Casalegno, F., Newton, T., Daher, R., Abdelaziz, M., Lodi-Rizzini, A., Schürmann, F., Krejci, I., & Markram, H. (2019) · Journal of Dental Research · doi:10.1177/0022034519871884 · Cited by 275
Baumgartl, H., Tomas, J., Buettner, R., & Merkel, M. (2020) · Progress in Additive Manufacturing · doi:10.1007/s40964-019-00108-3 · Cited by 268
“Inception modules have enabled a significant improvement in classification performance while simultaneously reducing the number of model parameters [41, 51, 55].”
BackgroundMethodInfluentialAutonomous Vehicles Enabled by the Integration of IoT, Edge Intelligence, 5G, and Blockchain
Biswas, A., & Wang, H.-C. (2023) · Sensors · doi:10.3390/s23041963 · Cited by 274
Sahlol, A. T., Kollmannsberger, P., & Ewees, A. A. (2020) · Scientific Reports · doi:10.1038/s41598-020-59215-9 · Cited by 274
Edge Intelligence: Empowering Intelligence to the Edge of Network
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., Crowcroft, J., & Hui, P. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3119950 · Cited by 272
Differentially Private Model Publishing for Deep Learning
Yu, L., Liu, L., Pu, C., Gursoy, M. E., & Truex, S. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00019 · Cited by 195
“training progresses, instead of using a constant learning rate throughout all epochs, to achieve better accuracy [3], [12].”
BackgroundTowards weeds identification assistance through transfer learning
Espejo-Garcia, B., Mylonas, N., Athanasakos, L., Fountas, S., & Vasilakoglou, I. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105306 · Cited by 271
HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation
Nirkin, Y., Wolf, L., & Hassner, T. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00405 · Cited by 254
Plant Disease Identification Using a Novel Convolutional Neural Network
Hassan, S. M., & Maji, A. K. (2022) · IEEE Access · doi:10.1109/access.2022.3141371 · Cited by 273
“Depthwise separable convolution introduced by Chollet [34] in the Xception model.”
MethodSAMNet: Stereoscopically Attentive Multi-Scale Network for Lightweight Salient Object Detection
Liu, Y., Zhang, X.-Y., Bian, J.-W., Zhang, L., & Cheng, M.-M. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3065239 · Cited by 271
“For BiSeNet [66], we report its results with ResNet-18 [43] ( i.e., BiSeNet R18) and Xception-39 [79] ( i.e., BiSeNet X39) backbones, respectively. a) Comparison with Existing SOD Methods: Table II shows the evaluation results of the proposed SAMNet compared with previous state-of-the-art…”
Deep diagnosis: A real-time apple leaf disease detection system based on deep learning
Khan, A. I., Quadri, S. M. K., Banday, S., & Latief Shah, J. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107093 · Cited by 264
Ko, H., Chung, H., Kang, W. S., Kim, K. W., Shin, Y., Kang, S. J., Lee, J. H., Kim, Y. J., Kim, N. Y., Jung, H., et al. (2020) · Journal of Medical Internet Research · doi:10.2196/19569 · Cited by 271
Deep Learning Techniques for Diabetic Retinopathy Classification: A Survey
Atwany, M. Z., Sahyoun, A. H., & Yaqub, M. (2022) · IEEE Access · doi:10.1109/access.2022.3157632 · Cited by 266
“Pre-trained CNN architectures ResNet50 [50], InceptionV3 [48], InceptionResNetV2 [51], Xception [52], and DenseNets [53] were finetuned for Diabetic Retinopathy classification.”
MethodLightweight Deep Learning for Resource-Constrained Environments: A Survey
Liu, H.-I., Galindo, M., Xie, H., Wong, L.-K., Shuai, H.-H., Li, Y.-H., & Cheng, W.-H. (2024) · ACM Computing Surveys · doi:10.1145/3657282 · Cited by 259
Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning
Desislavov, R., Martínez-Plumed, F., & Hernández-Orallo, J. (2023) · Sustainable Computing: Informatics and Systems · doi:10.1016/j.suscom.2023.100857 · Cited by 269
Waytowich, N., Lawhern, V. J., Garcia, J. O., Cummings, J., Faller, J., Sajda, P., & Vettel, J. M. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aae5d8 · Cited by 262
“The Compact-CNN also uses separable convolutions to more efficiently combine information across filters [43].”
MethodLi, J., Chen, J., Sheng, B., Li, P., Yang, P., Feng, D. D., & Qi, J. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3085669 · Cited by 264
“In the past ten years, the algorithms for image classification mainly include VGG16 [32], Xception [33], MobileNet [34], ResNet50, and ResNet101 [35].”
MethodEnhanced Deep Image Prior for Unsupervised Hyperspectral Image Super-Resolution
Li, J., Zheng, K., Gao, L., Han, Z., Li, Z., & Chanussot, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3531646 · Cited by 250
“Therefore, the depthwise convolution proposed by Chollet [99] is introduced to model such bandwise blurring with one shared PSF kernel, which is formulated as Here, F z ( ·; θ ( PSF ) ) denotes the spatial degradation and θ ( PSF ) serves as the PSF parameters.”
Asymmetric Siamese Networks for Semantic Change Detection in Aerial Images
Yang, K., Xia, G.-S., Liu, Z., Du, B., Yang, W., Pelillo, M., & Zhang, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3113912 · Cited by 261
MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
Qiu, Y., Zhang, K., Wang, C., Luo, W., Li, H., & Jin, Z. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01176 · Cited by 257
Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering
Li, X., Song, J., Gao, L., Liu, X., Huang, W., He, X., & Gan, C. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018658 · Cited by 259
Tian, Z., He, T., Shen, C., & Yan, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00324 · Cited by 252
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
Zou, Y., Zhang, Z., Zhang, H., Li, C., Bian, X., Huang, J., & Pfister, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.09713 · Cited by 195
“Unless spec-ified, we adopt the DeepLabv3+ model with Xception-65 (Chollet, 2017) as the feature backbone, which is pre-trained on the ImageNet dataset (Russakovsky et al., 2015).”
MethodAutomatic detection of COVID-19 infection using chest X-ray images through transfer learning
Ohata, E. F., Bezerra, G. M., Chagas, J. V. S. D., Lira Neto, A. V., Albuquerque, A. B., Albuquerque, V. H. C. D., & Reboucas Filho, P. P. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2020.1003393 · Cited by 265
Causal Discovery with Attention-Based Convolutional Neural Networks
Nauta, M., Bucur, D., & Seifert, C. (2019) · Machine Learning and Knowledge Extraction · doi:10.3390/make1010019 · Cited by 262
“A depthwise separable architecture improves accuracy and convergence speed [47], and the separate channels allow us to correctly interpret the relation between an input time series and the target time series, without mixing the inputs.”
BackgroundMethodEdge Intelligence in Intelligent Transportation Systems: A Survey
Gong, T., Zhu, L., Yu, F. R., & Tang, T. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3275741 · Cited by 256
Infrared small target segmentation networks: A survey
Kou, R., Wang, C., Peng, Z., Zhao, Z., Chen, Y., Han, J., Huang, F., Yu, Y., & Fu, Q. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109788 · Cited by 257
Kattenborn, T., Eichel, J., & Fassnacht, F. E. (2019) · Scientific Reports · doi:10.1038/s41598-019-53797-9 · Cited by 260
A systematic review of deep learning techniques for plant diseases
Pacal, I., Kunduracioglu, I., Alma, M. H., Deveci, M., Kadry, S., Nedoma, J., Slany, V., & Martinek, R. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10944-7 · Cited by 250
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
Tramèr, F., & Boneh, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03287 · Cited by 233
“Removing these activations improves convergence and accuracy (Chollet, 2017; Sheng et al., 2018), while also making the network more outsourcing-friendly (i.e., it is possible to verify a separable convolution in a single step).”
BackgroundJi, Y., Zhang, H., Zhang, Z., & Liu, M. (2021) · Information Sciences · doi:10.1016/j.ins.2020.09.003 · Cited by 262
Neural Video Compression with Diverse Contexts
Li, J., Li, B., & Lu, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02166 · Cited by 252
“The first is that, considering depthwise separable convolution [10] can reduce the computation cost while alleviating over-fitting, we widely use it to replace the normal convolution in the basic block design.”
MethodDeep multimodal fusion for semantic image segmentation: A survey
Zhang, Y., Sidibé, D., Morel, O., & Mériaudeau, F. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2020.104042 · Cited by 261
“Besides, many elaborated backbone networks, such as VGGNet [81], ResNet [82], and Xception [172], are widely used in a variety of segmentation network 635”
BackgroundAttention Receptive Pyramid Network for Ship Detection in SAR Images
Zhao, Y., Zhao, L., Xiong, B., & Kuang, G. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2997081 · Cited by 260
“In the method, a backbone network, composed of several layers of depth separable convolution [41], was established to extract basic features.”
MethodSaleem, M. H., Potgieter, J., & Arif, K. M. (2020) · Plants · doi:10.3390/plants9101319 · Cited by 259
“Therefore, future studies should propose another version of DL architecture that can achieve Xception-level accuracy and require smaller training time for each epoch.”
MethodInfluentialA smart municipal waste management system based on deep-learning and Internet of Things
Wang, C., Qin, J., Qu, C., Ran, X., Liu, C., & Chen, B. (2021) · Waste Management · doi:10.1016/j.wasman.2021.08.028 · Cited by 259
Machine Learning for Microcontroller-Class Hardware: A Review
Saha, S. S., Sandha, S. S., & Srivastava, M. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3210773 · Cited by 253
“MobileNetsV1 [12] introduced depthwise separable convolution [11] (channel-wise convolution followed by bottleneck layer), and width and resolution multipliers to control layer width and input resolution of AlexNet.”
BackgroundDeep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
Hong, Y., Pan, H., Sun, W., & Jia, Y. (2021) · arXiv · doi:10.48550/arxiv.2101.06085 · Cited by 261
“3) Lightweight Encoders: There are many computationally efficient backbones can be used as the encoder, such as MobileNet [32], ShuffleNet [33] and small version of Xception [34].”
MethodTowards Effective Low-Bitwidth Convolutional Neural Networks
Zhuang, B., Shen, C., Tan, M., Liu, L., & Reid, I. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00826 · Cited by 251
Forest fire and smoke detection using deep learning-based learning without forgetting
Sathishkumar, V. E., Cho, J., Subramanian, M., & Naren, O. S. (2023) · Fire Ecology · doi:10.1186/s42408-022-00165-0 · Cited by 259
MambaOut: Do We Really Need Mamba for Vision?
Yu, W., & Wang, X. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.00423 · Cited by 228
“Specifically, we specify the token mixer of Gated CNN as depthwise convolution [13] of 7 × 7 kernel size, following ConvNeXt [58, 61].”
Large image datasets: A pyrrhic win for computer vision?
Birhane, A., & Prabhu, V. U. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00158 · Cited by 257
“Various highly cited and celebrated papers in recent years [10, 16, 41, 77], for example, have used the unspoken unicorn amongst large scale vision datasets, that is, the JFT-300M dataset [?]”
BackgroundDeep learning wavefront sensing
Nishizaki, Y., Valdivia, M., Horisaki, R., Kitaguchi, K., Saito, M., Tanida, J., & Vera, E. (2019) · Optics Express · doi:10.1364/oe.27.000240 · Cited by 253
Collaborative Video Object Segmentation by Foreground-Background Integration
Yang, Z., Wei, Y., & Yang, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58558-7_20 · Cited by 257
RangeDet: In Defense of Range View for LiDAR-based 3D Object Detection
Fan, L., Xiong, X., Wang, F., Wang, N., & Zhang, Z. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00291 · Cited by 257
“Standard Conv 2D Grid Network parameter Matrix multiplication Channel-wise summation Depth-wise Conv [3] 2D Grid Network parameter Element-wise product Channel-wise summation RCD [1] 2D Learned dilation Network parameter Matrix multiplication Channel-wise summation Deformable Conv [4] 2D Learned offset Network paramet…”
MethodAttention Res-UNet with Guided Decoder for semantic segmentation of brain tumors
Maji, D., Sigedar, P., & Singh, M. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103077 · Cited by 255
Automatic Bridge Crack Detection Using a Convolutional Neural Network
Xu, H., Su, X., Wang, Y., Cai, H., Cui, K., & Chen, X. (2019) · Applied Sciences · doi:10.3390/app9142867 · Cited by 253
A comparative study of deep learning architectures on melanoma detection
Hosseinzadeh Kassani, S., & Hosseinzadeh Kassani, P. (2019) · Tissue and Cell · doi:10.1016/j.tice.2019.04.009 · Cited by 253
A Survey on Deepfake Video Detection
Yu, P., Xia, Z., Fei, J., & Lu, Y. (2021) · IET Biometrics · doi:10.1049/bme2.12031 · Cited by 253
“evaluated XceptionNet [29] on the FaceForensic++ dataset, outperforming all other networks in detecting fakes.”
MethodInfluentialA CNN Accelerator on FPGA Using Depthwise Separable Convolution
Bai, L., Zhao, Y., & Huang, X. (2018) · IEEE Transactions on Circuits and Systems II: Express Briefs · doi:10.1109/tcsii.2018.2865896 · Cited by 254
Computer Vision Techniques in Manufacturing
Zhou, L., Zhang, L., & Konz, N. (2023) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2022.3166397 · Cited by 248
EPOS: Estimating 6D Pose of Objects With Symmetries
Hodan, T., Barath, D., & Matas, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01172 · Cited by 249
Face Mask Detection Using Transfer Learning of InceptionV3
Jignesh Chowdary, G., Punn, N. S., Sonbhadra, S. K., & Agarwal, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-66665-1_6 · Cited by 250
“rning boosts the performance of the new model even when it is trained on a small dataset. There are several pretrained models like InceptionV3, Xception, MobileNet, MobileNetV2, VGG16, ResNet50, etc. [25,5,10,23,15,9] that are trained with 14 million images from the ImageNet dataset. InceptionV3 is a 48 layered convol…”
Background
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.