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 1,001–1,100 of 1,227
Deep learning: as the new frontier in high-throughput plant phenotyping
Arya, S., Sandhu, K. S., Singh, J., & Kumar, S. (2022) · Euphytica · doi:10.1007/s10681-022-02992-3 · Cited by 124
Yu, Q., Wang, H., Qiao, S., Collins, M. D., Zhu, Y., Adam, H., Yuille, A., & Chen, L.-C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19818-2_17 · Cited by 209
FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset
Khalid, H., Tariq, S., Kim, M., & Woo, S. S. (2021) · arXiv · doi:10.48550/arxiv.2108.05080 · Cited by 116
“On the other hand, EfficientNet-B0 outperformed Xception [72] on this task, though Xception is the best performer on other deepfake datasets such as FaceForensics++ [36].”
BackgroundMethodSiam R-CNN: Visual Tracking by Re-Detection
Voigtlaender, P., Luiten, J., Torr, P. H. S., & Leibe, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00661 · Cited by 115
Automatic classification of leukocytes using deep neural network
Yu, W., Chang, J., Yang, C., Zhang, L., Shen, H., Xia, Y., & Sha, J. (2017) · IEEE International Conference on ASIC (ASICON) · doi:10.1109/asicon.2017.8252657 · Cited by 115
Large-Scale Detection and Categorization of Oil Spills from SAR Images with Deep Learning
Bianchi, F. M., Espeseth, M. M., & Borch, N. T. (2020) · Remote Sensing · doi:10.3390/rs12142260 · Cited by 137
Fast and Accurate Model Scaling
Dollar, P., Singh, M., & Girshick, R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00098 · Cited by 113
Kamran, S. A., Hossain, K. F., Tavakkoli, A., Zuckerbrod, S. L., Sanders, K. M., & Baker, S. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87237-3_4 · Cited by 155
Masked Face Recognition Using Deep Learning: A Review
Alzu’bi, A., Albalas, F. A., Al-Hadhrami, T., Younis, L. B., & Bashayreh, A. (2021) · Electronics · doi:10.3390/electronics10212666 · Cited by 141
“Xception [66] is an extreme version of inception that replaces the modules of inception with depth-wise separable convolutions.”
BackgroundBeyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection
Luo, A., Kong, C., Huang, J., Hu, Y., Kang, X., & Kot, A. C. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3332218 · Cited by 115
“We train all models on the FF ++ (C23) set and evaluate intra-dataset performance on the FF ++ (C23) test set and cross-dataset performance on CDF and WDF datasets.”
MethodSqueezeBERT: What can computer vision teach NLP about efficient neural networks?
Iandola, F., Shaw, A., Krishna, R., & Keutzer, K. (2020) · Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing · doi:10.18653/v1/2020.sustainlp-1.17 · Cited by 114
Towards Generalizable Deepfake Detection with Locality-aware AutoEncoder
Du, M., Pentyala, S., Li, Y., & Hu, X. (2020) · Proceedings of the 29th ACM International Conference on Information & Knowledge Management · doi:10.1145/3340531.3411892 · Cited by 114
“• XceptionNet: This is a CNN network based on separable convolutions with residual connections [6].”
Background(2020) · doi:10.1007/978-3-030-68821-9_38 · Cited by 113
Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors
Khalid, H., Kim, M., Tariq, S., & Woo, S. S. (2021) · Proceedings of the 1st Workshop on Synthetic Multimedia - Audiovisual Deepfake Generation and Detection · doi:10.1145/3476099.3484315 · Cited by 110
Deepfake Detection: A Comprehensive Survey from the Reliability Perspective
Wang, T., Liao, X., Chow, K. P., Lin, X., & Wang, Y. (2025) · ACM Computing Surveys · doi:10.1145/3699710 · Cited by 107
“Then the models are further discussed regarding the reliability following Algorithm 1 along with case studies on real-life Deepfake materials.”
InfluentialFace Forgery Detection by 3D Decomposition
Zhu, X., Wang, H., Fei, H., Lei, Z., & Li, S. Z. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00295 · Cited by 106
Neural Architecture Search Survey: A Hardware Perspective
Chitty-Venkata, K. T., & Somani, A. K. (2023) · ACM Computing Surveys · doi:10.1145/3524500 · Cited by 106
“(1) MobileNetV1-space [51] uses a series of Depthwise-Separable Convolutions [16] for efficient inference on mobile phones with search element being number of filters in each block.”
MethodRotation-Oriented Collaborative Self-Supervised Learning for Retinal Disease Diagnosis
Li, X., Hu, X., Qi, X., Yu, L., Zhao, W., Heng, P.-A., & Xing, L. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3075244 · Cited by 105
Embedded Intelligence on FPGA: Survey, Applications and Challenges
Seng, K. P., Lee, P. J., & Ang, L. M. (2021) · Electronics · doi:10.3390/electronics10080895 · Cited by 105
“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].”
MethodBalamuralidhar, N., Tilon, S., & Nex, F. (2021) · Remote Sensing · doi:10.3390/rs13040573 · Cited by 104
Chen, T.-H. K., Qiu, C., Schmitt, M., Zhu, X. X., Sabel, C. E., & Prishchepov, A. V. (2020) · Remote Sensing of Environment · doi:10.1016/j.rse.2020.112096 · Cited by 104
“4), we used the Xception architecture (Chollet 2017).”
MethodFakeLocator: Robust Localization of GAN-Based Face Manipulations
Huang, Y., Juefei-Xu, F., Guo, Q., Liu, Y., & Pu, G. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3141262 · Cited by 102
“For [27], in the literature, the authors insert an attention map module into a classifier such as Xception [31] to obtain the location of fake regions.”
MethodProblems and opportunities in training deep learning software systems: an analysis of variance
Pham, H. V., Qian, S., Wang, J., Lutellier, T., Rosenthal, J., Tan, L., Yu, Y., & Nagappan, N. (2020) · Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/3324884.3416545 · Cited by 100
“Following common practice [14, 24, 45, 51, 62, 97, 102], we use the validation set to select the best model.”
MethodFuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data
Krispel, G., Opitz, M., Waltner, G., Possegger, H., & Bischof, H. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093584 · Cited by 99
“We are even better than the powerful Xception65 DeepLabv3+ on average performance, despite using the weaker backend.”
MethodFactorization tricks for LSTM networks
Kuchaiev, O., & Ginsburg, B. (2017) · arXiv · doi:10.48550/arxiv.1703.10722 · Cited by 99
“This multi-group approach was extended to the extreme in Xception architecture by Chollet (2016).”
MethodWildfire and Smoke Detection Using Staged YOLO Model and Ensemble CNN
Bahhar, C., Ksibi, A., Ayadi, M., Jamjoom, M. M., Ullah, Z., Soufiene, B. O., & Sakli, H. (2023) · Electronics · doi:10.3390/electronics12010228 · Cited by 99
“The study employs a binary classification model using binary crossentropy (BCN) loss and some state-of-the-art CNNs, such as Google’s Xception network [29], which is a deep convolutional neural network; MobileNetV2, proposed by Sandler et al.”
MethodLe, T.-N., Nguyen, H. H., Yamagishi, J., & Echizen, I. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00996 · Cited by 97
“, XceptionNet [6]) to reject lowquality fake images.”
BackgroundExploring Frequency Adversarial Attacks for Face Forgery Detection
Jia, S., Ma, C., Yao, T., Yin, B., Ding, S., & Yang, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00407 · Cited by 97
“Dataset EfficientNet b4 [43] ResNet 50 [20] XceptionNet [6] F(3)-Net [5] LRL [36]”
InfluentialPassive acoustic monitoring of animal populations with transfer learning
Dufourq, E., Batist, C., Foquet, R., & Durbach, I. (2022) · Ecological Informatics · doi:10.1016/j.ecoinf.2022.101688 · Cited by 97
Yu, H., Zhang, L., Wang, W., Li, S., Chen, S., Yang, S., Li, J., & Liu, X. (2023) · Energy · doi:10.1016/j.energy.2023.127846 · Cited by 96
TALL: Thumbnail Layout for Deepfake Video Detection
Xu, Y., Liang, J., Jia, G., Yang, Z., Zhang, Y., & He, R. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02071 · Cited by 109
SSTNet: Detecting Manipulated Faces Through Spatial, Steganalysis and Temporal Features
Wu, X., Xie, Z., Gao, Y., & Xiao, Y. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053969 · Cited by 94
“Specifically, spatial features are extracted by a deep model XceptionNet [16] for detecting middle-level and high-level artifacts (blue box in Fig.”
BackgroundMethodDeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
Yan, Z., Zhang, Y., Yuan, X., Lyu, S., & Wu, B. (2023) · arXiv · doi:10.48550/arxiv.2307.01426 · Cited by 97
“This detector utilizes the Xception back-bone [5].”
MethodInfluentialNGUYEN, D., MEJRI, N., SINGH, I. P., KULESHOVA, P., ASTRID, M., KACEM, A., GHORBEL, E., & AOUADA, D. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01647 · Cited by 93
“These common architectures, such as XceptionNet [9] and EfficientNet [44], tend to learn global features, ignoring more localized cues [50, 55].”
BackgroundMethodDynamic Difference Learning With Spatio–Temporal Correlation for Deepfake Video Detection
Yin, Q., Lu, W., Li, B., & Huang, J. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3290752 · Cited by 92
Noise Based Deepfake Detection via Multi-Head Relative-Interaction
Wang, T., & Chow, K. P. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26701 · Cited by 93
“The depth-wise separable convolution idea is introduced by Chollet (Chollet 2017) to avoid the possible overfitting and time-consuming problem of CNNs during model training.”
BackgroundOne Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework
Tariq, S., Lee, S., & Woo, S. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3449809 · Cited by 91
“Xception: Xception Network [8] is considered as the state-of-theart deep learning model for image classification task.”
BackgroundMethodInfluentialLarge image datasets: A pyrrhic win for computer vision?
Prabhu, V. U., & Birhane, A. (2020) · arXiv · doi:10.48550/arxiv.2006.16923 · Cited by 91
Using deep transfer learning to detect scoliosis and spondylolisthesis from x-ray images
Fraiwan, M., Audat, Z., Fraiwan, L., & Manasreh, T. (2022) · PLOS ONE · doi:10.1371/journal.pone.0267851 · Cited by 90
“The architecture improves on the Inception network by replacing the standard inception modules with depthwise separable convolutions [39].”
MethodDetecting Deepfakes with Metric Learning
Kumar, A., Bhavsar, A., & Verma, R. (2020) · 2020 8th International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf49977.2020.9107962 · Cited by 90
“In our work, we used Xception [12] architecture”
MethodDFDT: An End-to-End DeepFake Detection Framework Using Vision Transformer
Khormali, A., & Yuan, J.-S. (2022) · Applied Sciences · doi:10.3390/app12062953 · Cited by 88
“Their design benefits from XceptionNet [47] as a backbone for image feature extraction and 12 transformer blocks for feature learning.”
MethodDetecting fake images by identifying potential texture difference
Yang, J., Xiao, S., Li, A., Lan, G., & Wang, H. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.06.043 · Cited by 86
Designing efficient accelerator of depthwise separable convolutional neural network on FPGA
Ding, W., Huang, Z., Huang, Z., Tian, L., Wang, H., & Feng, S. (2019) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2018.12.008 · Cited by 85
State-dependent pupil dilation rapidly shifts visual feature selectivity
Franke, K., Willeke, K. F., Ponder, K., Galdamez, M., Zhou, N., Muhammad, T., Patel, S., Froudarakis, E., Reimer, J., Sinz, F. H., et al. (2022) · Nature · doi:10.1038/s41586-022-05270-3 · Cited by 85
A Compact Convolutional Neural Network for Surface Defect Inspection
Huang, Y., Qiu, C., Wang, X., Wang, S., & Yuan, K. (2020) · Sensors · doi:10.3390/s20071974 · Cited by 85
“Using this super large dataset, researchers pretrain a 65-layer Xception [33] model, then fine-tune a segmentation model based on PASCAL VOC 2012.”
MethodA Capsule Network Based Approach for Detection of Audio Spoofing Attacks
Luo, A., Li, E., Liu, Y., Kang, X., & Wang, Z. J. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9414670 · Cited by 84
Emerging trends in autonomous vehicle perception: Multimodal fusion for 3D object detection
Alaba, S. Y., Gurbuz, A. C., & Ball, J. E. (2024) · World Electric Vehicle Journal · doi:10.3390/wevj15010020 · Cited by 82
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions
Gao, H., Wang, Z., Cai, L., & Ji, S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2975796 · Cited by 81
Lewis, J. K., Toubal, I. E., Chen, H., Sandesera, V., Lomnitz, M., Hampel-Arias, Z., Prasad, C., & Palaniappan, K. (2020) · 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) · doi:10.1109/aipr50011.2020.9425167 · Cited by 80
Liu, X., Yang, J., Zou, C., Chen, Q., Yan, X., Chen, Y., & Cai, C. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3059318 · Cited by 79
Video Transformer for Deepfake Detection with Incremental Learning
Khan, S. A., & Dai, H. (2021) · Proceedings of the 29th ACM International Conference on Multimedia · doi:10.1145/3474085.3475332 · Cited by 79
“They employ a simple Xception [12] network pre-trained on imagenet dataset, and � ne-tune it on FaceForensics++ dataset.”
MethodSeeing is Believing: Exploring Perceptual Differences in DeepFake Videos
Tahir, R., Batool, B., Jamshed, H., Jameel, M., Anwar, M., Ahmed, F., Zaffar, M. A., & Zaffar, M. F. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445699 · Cited by 79
“The result is fed into a learned classifcation network that outputs the prediction using an XceptionNet architecture [7].”
Insu-YOLO: An Insulator Defect Detection Algorithm Based on Multiscale Feature Fusion
Chen, Y., Liu, H., Chen, J., Hu, J., & Zheng, E. (2023) · Electronics · doi:10.3390/electronics12153210 · Cited by 78
“On the other hand, lightweight networks such as Xception [17], MobileNets [18–20], and ShuffleNets [21,22] greatly improve the detection speed by depth-wise separable convolution, but their lower detection accuracy renders them unsuitable for power inspection tasks.”
BackgroundFighting Fake News: Two Stream Network for Deepfake Detection via Learnable SRM
Han, B., Han, X., Zhang, H., Li, J., & Cao, X. (2021) · IEEE Transactions on Biometrics, Behavior, and Identity Science · doi:10.1109/tbiom.2021.3065735 · Cited by 77
An Aggregated-Based Deep Learning Method for Leukemic B-lymphoblast Classification
Kasani, P. H., Park, S.-W., & Jang, J.-W. (2020) · Diagnostics · doi:10.3390/diagnostics10121064 · Cited by 76
“After dataset pre-processing, we employed various state-of-the-art deep CNN architectures, namely InceptionV3, AlexNet, DenseNet201, VGGNet-16, VGGNet19, Xception, MobileNet, ShuffleNet, and two NASNet models.”
BackgroundInfluentialA Contemporary Survey on Deepfake Detection: Datasets, Algorithms, and Challenges
Gong, L. Y., & Li, X. J. (2024) · Electronics · doi:10.3390/electronics13030585 · Cited by 75
“For example, there is a video transformer with the incremental learning approach [42] published in 2021, which utilizes Xception [29] as the backbone and 12 transformer blocks to learn feature correlations.”
BackgroundMethodAdvancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence
Bai, X., Wang, H., Ma, L., Xu, Y., Gan, J., Fan, Z., Yang, F., Ma, K., Yang, J., Bai, S., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-021-00421-z · Cited by 75
Hu, J., Cui, C., Yang, W., Huang, L., Yu, R., Liu, S., & Kong, Y. (2021) · Translational Oncology · doi:10.1016/j.tranon.2020.100921 · Cited by 75
“To convert these center tiles to informative features, Xception [16] neural network with ImageNet pre-trained parameters is applied to extract 2048-dimensional feature vectors.”
MethodMekruksavanich, S., & Jitpattanakul, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-39080-y · Cited by 75
Miller, J., Taori, R., Raghunathan, A., Sagawa, S., Koh, P. W., Shankar, V., Liang, P., Carmon, Y., & Schmidt, L. (2021) · arXiv · doi:10.48550/arxiv.2107.04649 · Cited by 74
Encrypted Network Traffic Analysis and Classification Utilizing Machine Learning
Alwhbi, I. A., Zou, C. C., & Alharbi, R. N. (2024) · Sensors · doi:10.3390/s24113509 · Cited by 81
“During the step of selecting a classification approach, there are various ways available, including machine-learning technologies, statistical methods (such as heuristics), and graphical technique methods (such as motifs and graphlets) [37].”
MethodSimões, M., Borra, D., Santamaría-Vázquez, E., GBT-UPM, Bittencourt-Villalpando, M., Krzemiński, D., Miladinović, A., Neural_Engineering_Group, Schmid, T., Zhao, H., et al. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.568104 · Cited by 72
“To this aim, architectures like EEGNet (Lawhern et al., 2018) were proposed including optimized convolutions, such as depthwise and separable convolutions (Chollet, 2016).”
MethodNTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results
Li, Y., Zhang, Y., Timofte, R., Van Gool, L., Yu, L., Li, Y., Li, X., Jiang, T., Wu, Q., Han, M., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00189 · Cited by 72
“Meanwhile, in the first 250 epochs, we use L1 loss, and in the last 50 epochs, we use L2 loss.”
MethodVision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space
Chavan, A., Shen, Z., Liu, Z., Liu, Z., Cheng, K.-T., & Xing, E. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00488 · Cited by 72
“The compression research extends from channel pruning [17,27,56], quantization and binarization [1, 9, 21, 29, 33, 63], knowledge distillation [18, 32, 36, 39–41], compact neural network de-sign [10,22,31,52,60] to architecture search [35,65,66].”
MethodPérez-Hernández, M., van Opbergen, C. J. M., Bagwan, N., Vissing, C. R., Marrón-Liñares, G. M., Zhang, M., Torres Vega, E., Sorrentino, A., Drici, L., Sulek, K., et al. (2022) · Circulation · doi:10.1161/circulationaha.122.060454 · Cited by 72
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
Yang, L., Jiang, H., Cai, R., Wang, Y., Song, S., Huang, G., & Tian, Q. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00357 · Cited by 71
“This issue has motivated a number of researchers on designing efficient CNN architectures [15, 3, 11, 40, 24, 31].”
BackgroundMuhammad, G., & Alhussein, M. (2021) · IEEE Access · doi:10.1109/access.2021.3090317 · Cited by 70
Explainable Deep-Fake Detection Using Visual Interpretability Methods
Malolan, B., Parekh, A., & Kazi, F. (2020) · 2020 3rd International Conference on Information and Computer Technologies (ICICT) · doi:10.1109/icict50521.2020.00051 · Cited by 70
“We will use the Xception network introduced by F. Chollet [13], which is a traditional CNN with Depth-wise Separable Convolutions.”
MethodLearning Multi-View Interactional Skeleton Graph for Action Recognition
Wang, M., Ni, B., & Yang, X. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3032738 · Cited by 67
“2, SPG-Conv shares a similar high-level spirit with separable convolution manner of CNN (e.g., MobileNet [54], Xception [55]).”
BackgroundDeepFake Detection Based on High-Frequency Enhancement Network for Highly Compressed Content
Gao, J., Xia, Z., Marcialis, G. L., Dang, C., Dai, J., & Feng, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123732 · Cited by 67
Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion
Wang, Y., Sun, F., Lu, M., & Yao, A. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413621 · Cited by 68
“In group convolutions [7, 15], outputs that correspond to each channel are only related with a portion of input channels.”
BackgroundMethodDeepfake forensics analysis: An explainable hierarchical ensemble of weakly supervised models
Silva, S. H., Bethany, M., Votto, A. M., Scarff, I. H., Beebe, N., & Najafirad, P. (2022) · Forensic Science International: Synergy · doi:10.1016/j.fsisyn.2022.100217 · Cited by 66
“Our overall decision combines the decisions of three networks: Xception [70], Xception + Augmentation, and Efficient-Net [71] + Augmentation.”
BackgroundMethodDF-Platter: Multi-Face Heterogeneous Deepfake Dataset
Narayan, K., Agarwal, H., Thakral, K., Mittal, S., Vatsa, M., & Singh, R. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00939 · Cited by 66
“XceptionNet [5] is based on depthwise separable convo-”
MethodFdftnet: facing off fake images using fake detection fine-tuning network
Jeon, H., Bang, Y., & Woo, S. S. (2020) · IFIP Advances in Information and Communication Technology · doi:10.1007/978-3-030-58201-2_28 · Cited by 65
“Xception [1] has been served as the baseline for fake image detection in [30,23].”
Deep Ensemble Model for Classification of Novel Coronavirus in Chest X‐Ray Images
Ahmad, F., Farooq, A., & Ghani, M. U. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/8890226 · Cited by 65
A survey of model compression strategies for object detection
Lyu, Z., Yu, T., Pan, F., Zhang, Y., Luo, J., Zhang, D., Chen, Y., Zhang, B., & Li, G. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17192-x · Cited by 65
Supervised Contrastive Learning for Generalizable and Explainable DeepFakes Detection
Xu, Y., Raja, K., & Pedersen, M. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw54805.2022.00044 · Cited by 62
Optical navigation for Lunar landing based on Convolutional Neural Network crater detector
Silvestrini, S., Piccinin, M., Zanotti, G., Brandonisio, A., Bloise, I., Feruglio, L., Lunghi, P., Lavagna, M., & Varile, M. (2022) · Aerospace Science and Technology · doi:10.1016/j.ast.2022.107503 · Cited by 65
On Improving Cross-dataset Generalization of Deepfake Detectors
Nadimpalli, A. V., & Rattani, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00019 · Cited by 79
“For instance, XceptionNet for deep fake detection obtained Area Under Curve (AUC) of 0.997 when trained and tested on FaceForensics++ dataset.”
BackgroundMethodInfluentialAssessing Image Quality Issues for Real-World Problems
Chiu, T.-Y., Zhao, Y., & Gurari, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00370 · Cited by 63
Cai, Z., Ghosh, S., Dhall, A., Gedeon, T., Stefanov, K., & Hayat, M. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103818 · Cited by 63
Grapy-ML: Graph Pyramid Mutual Learning for Cross-Dataset Human Parsing
He, H., Zhang, J., Zhang, Q., & Tao, D. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6728 · Cited by 62
Caroppo, A., Leone, A., & Siciliano, P. (2020) · Journal of Computer Science and Technology · doi:10.1007/s11390-020-9665-4 · Cited by 60
AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
Cai, Z., Ghosh, S., Adatia, A. P., Hayat, M., Dhall, A., Gedeon, T., & Stefanov, K. (2024) · Proceedings of the 32nd ACM International Conference on Multimedia · doi:10.1145/3664647.3680795 · Cited by 59
“Here we provide further details on the user study (see Section 3.3) that aims to evaluate humans’ performance in detecting the highly realistic deepfake content in AV-Deepfake1M.”
InfluentialAV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
Cai, Z., Ghosh, S., Adatia, A. P., Hayat, M., Dhall, A., Gedeon, T., & Stefanov, K. (2023) · arXiv · doi:10.48550/arxiv.2311.15308 · Cited by 59
Rizzoli, G., Barbato, F., & Zanuttigh, P. (2022) · Technologies · doi:10.3390/technologies10040090 · Cited by 58
TOW-IDS: Intrusion detection system based on three overlapped wavelets for automotive ethernet
Han, M. L., Kwak, B. I., & Kim, H. K. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3221893 · Cited by 58
Hsu, S.-T., Su, Y.-J., Hung, C.-H., Chen, M.-J., Lu, C.-H., & Kuo, C.-E. (2022) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-02047-6 · Cited by 58
“Finally, an ensemble network model was formed using ResNet-18, ResNet-50, and Xception for final ensemble learning.”
BackgroundInfluentialA lightweight 3D convolutional neural network for deepfake detection
Liu, J., Zhu, K., Lu, W., Luo, X., & Zhao, X. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22499 · Cited by 57
Cyberbullying detection using deep transfer learning
Roy, P. K., & Mali, F. U. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00772-z · Cited by 57
Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging
Kumar, R., Khan, A. A., Kumar, J., Zakria, Golilarz, N. A., Zhang, S., Ting, Y., Zheng, C., & Wang, W. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3076767 · Cited by 57
Ramadhani, K. N., Munir, R., & Utama, N. P. (2024) · IEEE Access · doi:10.1109/access.2024.3352890 · Cited by 57
“In this research, the deepfake detection algorithm that has the highest accuracy is the XceptionNet [12] model which is a deep feature approach.”
MethodResultInfluentialExploring Disentangled Content Information for Face Forgery Detection
Liang, J., Shi, H., & Deng, W. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19781-9_8 · Cited by 58
Domain Generalization via Aggregation and Separation for Audio Deepfake Detection
Xie, Y., Cheng, H., Wang, Y., & Ye, L. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3324724 · Cited by 59
Locate and Verify: A Two-Stream Network for Improved Deepfake Detection
Shuai, C., Zhong, J., Wu, S., Lin, F., Wang, Z., Ba, Z., Liu, Z., Cavallaro, L., & Ren, K. (2023) · Proceedings of the 31st ACM International Conference on Multimedia · doi:10.1145/3581783.3612386 · Cited by 55
“Xception-Reg [9] utilizes an attention mechanism to highlight informative regions, thereby improving the binary classification.”
MethodInfluentialSpoC: Spoofing Camera Fingerprints
Cozzolino, D., Thies, J., Rossler, A., Niesner, M., & Verdoliva, L. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00110 · Cited by 54
“In general, most successful solutions are based on very deep networks [50, 24, 11], that perform well even when data are subjected to common postprocessing operations, like the re-compression routinely performed when uploading images on social networks.”
BackgroundInfluentialDepth map guided triplet network for deepfake face detection
Liang, B., Wang, Z., Huang, B., Zou, Q., Wang, Q., & Liang, J. (2023) · Neural Networks · doi:10.1016/j.neunet.2022.11.031 · Cited by 54
ADD: Attention-Based DeepFake Detection Approach
Khormali, A., & Yuan, J.-S. (2021) · Big Data and Cognitive Computing · doi:10.3390/bdcc5040049 · Cited by 55
Assessment framework for deepfake detection in real-world situations
Lu, Y., & Ebrahimi, T. (2024) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-024-00621-8 · Cited by 60
“The two detectors present exceptional performance on unaltered FFpp and CelebDFv2 testing data as expected, but then show severe performance deterioration on all kinds of modified data from the assessment framework, which indicates a lack of robustness.”
BackgroundNguyen, X. H., Tran, T. S., Le, V. T., Nguyen, K. D., & Truong, D.-T. (2021) · Forensic Science International: Digital Investigation · doi:10.1016/j.fsidi.2021.301108 · Cited by 53
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.