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
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
“Depthwise Separable Convolutions are a key building block for many efficient neural network architectures [27, 28, 20] and we use them in the present work as well.”
MethodCBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063
“However, given the design of state-of-art neural networks [38, 68, 70, 27, 12] and limited GPU memory, it is computationally prohibitive to extract output feature maps that are 8, or even 4 times smaller than the input resolution.”
BackgroundMethodInfluentialEncoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
“In prior work, cross-channel correlations are typically mapped as new combinations of features, either independently of spatial structure [22], [23] or jointly by using standard convolutional filters [24] with 1 1 convolutions.”
MethodShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00716 · Cited by 9,982
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1707.01083 · Cited by 9,982
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841
“Notably, to further improve the effi-ciency, we use depthwise separable convolution [4, 29] for feature fusion, and add batch normalization and activation after each convolution.”
MethodECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., & Hu, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01155 · Cited by 9,641
“From perspective of efficient convolutions (Zhang et al. 2017; Xie et al. 2017), SE-Var2 can be regarded as a depth-wise separable convolution (Chollet 2017).”
InfluentialLiu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01167 · Cited by 8,494
“Depthwise conv has been popularized by MobileNet [34] and Xception [11].”
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
Learning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00907 · Cited by 7,831
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ma, N., Zhang, X., Zheng, H.-T., & Sun, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01264-9_8 · Cited by 7,356
“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.”
BackgroundMethodInfluentialMachine learning: Algorithms, real-world applications and research directions
Sarker, I. H. (2021) · SN Computer Science · doi:10.1007/s42979-021-00592-x · Cited by 5,583
“A number of advanced deep learning models based on CNN can be used in the field, such as AlexNet [60], Xception [24], In-Preprints ception [118], Visual Geometry Group (VGG) [44], ResNet [45], etc. – LSTM-RNN: Long short-term memory (LSTM) is an artificial recurrent neural network (RNN) architecture…”
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3084827 · Cited by 5,273
GhostNet: More Features From Cheap Operations
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00165 · Cited by 5,222
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215
“, applied only on one of the input channels) followed by 1 × 1 3-D convolutions as demonstrated in Xception [155] and MobileNets [156].”
MethodKnowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931
“Recently, depth-wise separable convolution has been widely used to design efficient neural networks for mobile or embedded devices (Chollet, 2017; Howard et al., 2017; Sandler et al., 2018; Zhang et al., 2018a; Ma et al., 2018).”
MethodObject Detection in 20 Years: A Survey
Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3238524 · Cited by 3,689
“3) Depthwise Separable Convolution: Depthwise separable convolution [142], as shown in Fig.”
Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1811.00982 · Cited by 3,653
“This model is trained on the JFT dataset – an internal Google dataset withmore than 300million imageswith noisy labels (Hinton et al. 2014; Chollet 2017).”
BackgroundMethodInfluentialWu, Y., & He, K. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01198-w · Cited by 3,601
“2017) andXception (Chollet 2017) exploit channel-wise (also called “depth-wise”) convolutions, which are group convolutions with a group number equal to the channel number.”
BackgroundMasked-attention Mask Transformer for Universal Image Segmentation
Cheng, B., Misra, I., Schwing, A. G., Kirillov, A., & Girdhar, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00135 · Cited by 3,565
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503
“Inspired by this, Chollet (2016) proposed the Xception architecture in which they replace the Inception building blocks with depth-wise separable convolutions (depth-wise convolution followed by a point-wise convolution).”
MethodRes2Net: A New Multi-Scale Backbone Architecture
Gao, S.-H., Cheng, M.-M., Zhao, K., Zhang, X.-Y., Yang, M.-H., & Torr, P. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2938758 · Cited by 3,385
“Recent years have witnessed numerous backbone networks [9], [17], [20], [22], [37], [39], [43], [47], achieving state-of-the-art performance in various vision tasks with stronger multi-scale representations.”
BackgroundFaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314
“(5) XceptionNet [13] is a traditional CNN trained on ImageNet based on separable convolutions with residual connections.”
BackgroundMethodA survey of the recent architectures of deep convolutional neural networks
Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09825-6 · Cited by 3,137
“Xception can be considered as an extreme Inception architecture, which exploits the idea of depthwise separable convolution (Chollet 2017).”
BackgroundBiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., & Sang, N. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01261-8_20 · Cited by 2,968
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965
“Research on CNN architectures remain active, and a numer of backbone networks are still emerging such as Dilated Residual Networks [230], Xception [35], DetNet [127], and Dual Path Networks (DPN) [31].”
BackgroundMethodInfluentialDeep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965
“Research on CNN architectures remain active, and a numer of backbone networks are still emerging such as Dilated Residual Networks [230], Xception [35], DetNet [127], and Dual Path Networks (DPN) [31].”
BackgroundMethodInfluentialRepVGG: Making VGG-style ConvNets Great Again
Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., & Sun, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01352 · Cited by 2,907
“, depthwise conv in Xception [3] and MobileNets [16, 30] and channel shuffle in ShuffleNets [24, 41]) increase the memory access cost and lack supports of various devices.”
BackgroundSarker, I. H. (2021) · SN Computer Science · doi:10.1007/s42979-021-00815-1 · Cited by 2,678
“Several variants of CNN are exist in the area that includes visual geometry group (VGG) [38], AlexNet [62], Xception [17], Inception [116], ResNet [39], etc. that can be used in various application domains according to their learning capabilities.”
BackgroundChannel Pruning for Accelerating Very Deep Neural Networks
He, Y., Zhang, X., & Sun, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.155 · Cited by 2,647
“Since computational complexity becomes important in model design, separable convolution has been payed much attention [50, 7].”
BackgroundMethodInfluentialCvT: Introducing Convolutions to Vision Transformers
Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., & Zhang, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00009 · Cited by 2,444
“…where x q/k/vi is the token input for Q/K/V matrices at layer i , x i is the unperturbed token prior to the Convolu-tional Projection, Conv2d is a depth-wise separable convolution [5] implemented by: Depth-wise Conv2d → BatchNorm2d → Point-wise Conv2d , and s refers to the convolution kernel size.”
BackgroundMethodInfluentialRun, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
Chen, J., Kao, S.-H., He, H., Zhuo, W., Wen, S., Lee, C.-H., & Chan, S.-H. G. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01157 · Cited by 2,343
“They have been widely adopted in mobile/edge-oriented networks, such as MobileNets [20, 21, 47], ShuffleNets [40, 76], GhostNet [13], EfficientNets [54, 55], TinyNet [14], Xception [8], CondenseNet [23, 70], TVConv [4], MnasNet [53], and FBNet [67].”
BackgroundMethodRevisiting Unreasonable Effectiveness of Data in Deep Learning Era
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.97 · Cited by 2,484
“We use the same mAP@100 metric as in [7], which is computed as the mean average precision (mAP) for top-100 predictions.”
BackgroundMethodInfluentialSelf-Training With Noisy Student Improves ImageNet Classification
Xie, Q., Luong, M.-T., Hovy, E., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01070 · Cited by 2,393
Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01316-z · Cited by 1,738
“This model is trained on the JFT dataset – an internal Google dataset withmore than 300million imageswith noisy labels (Hinton et al. 2014; Chollet 2017).”
BackgroundMethodInfluentialApostolopoulos, I. D., & Mpesiana, T. A. (2020) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-020-00865-4 · Cited by 2,338
“eter Description VGG19 [10] Layer Cutoff 18 Neural Network 1024 nodes Mobile Net [11] Layer Cutoff 10 Neural Network 1000 nodes, 750 nodes Inception [12] Layer Cutoff 249 Neural Network 1000 Xception [13] Layer Cutoff 120 Neural Network 1000 nodes, 750 nodes Inception ResNet v2 [12] Layer Cutoff 730 Neural Network No…”
BackgroundInfluentialOpportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
“Because many of the latest neural network architectures (ResNet, Inception, Xception, and others) are already optimized for and pretrained on generic, large-scale image datasets [259], encoding genomic data as images could prove to be a generally effective and efficient strategy.”
BackgroundGCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond
Cao, Y., Xu, J., Lin, S., Wei, F., & Hu, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00246 · Cited by 2,307
“ResNeXt [34] and Xception [4] adopt group convolution to increase cardinality.”
BackgroundMLP-Mixer: An all-MLP Architecture for Vision
Tolstikhin, I., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2105.01601 · Cited by 2,087
“For example, separable convolutions [9, 40], used in some CNNs, apply convolutions to each channel independently of the other channels.”
BackgroundMethodConv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech Separation
Luo, Y., & Mesgarani, N. (2019) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2915167 · Cited by 2,042
“Depthwise separable convolution (also referred to as separable convolution) has proven effective in image processing tasks [32], [33] and neural machine translation tasks [39].”
BackgroundMethodDeep Learning for Image Super-Resolution: A Survey
Wang, Z., Chen, J., & Hoi, S. C. H. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2982166 · Cited by 1,969
MesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846
“• Xception [40] corresponds to a DeepFake detection method based on the XceptionNet model [12] trained on the FaceForensics++ dataset.”
MethodReview on Convolutional Neural Networks (CNN) in vegetation remote sensing
Kattenborn, T., Leitloff, J., Schiefer, F., & Hinz, S. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.12.010 · Cited by 1,805
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation
Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., & Sang, N. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01515-2 · Cited by 1,813
“The concept of our BiSeNet is generic, which can be implemented with different convolutional models (He et al., 2016; Huang et al., 2017; Chollet, 2017; Iandola et al., 2016; Howard et al., 2017; Sandler et al., 2018; Zhang et al., 2018b; Ma et al., 2018) and any specific designs.”
BackgroundMethodInfluentialUnsupervised Data Augmentation for Consistency Training
Xie, Q., Dai, Z., Hovy, E., Luong, M.-T., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1904.12848 · Cited by 1,517
“…keeps roughly 10% of the supervised data while using all other ImageNet data as unlabeled data, (b) Secondly, we consider the fully supervised scenario where we keep all images in ImageNet as supervised data and obtain extra unlabeled data from the JFT dataset [Hinton et al., 2015, Chollet, 2017].”
MethodCSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
Li, Y., Zhang, X., & Chen, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00120 · Cited by 1,698
AutoML: A survey of the state-of-the-art
He, X., Zhao, K., & Chu, X. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106622 · Cited by 1,691
A State-of-the-Art Survey on Deep Learning Theory and Architectures
Alom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M. S., Hasan, M., Van Essen, B. C., Awwal, A. A. S., & Asari, V. K. (2019) · Electronics · doi:10.3390/electronics8030292 · Cited by 1,620
Relation Networks for Object Detection
Hu, H., Gu, J., Zhang, Z., Dai, J., & Wei, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00378 · Cited by 1,524
Automated Machine Learning: Methods, Systems, Challenges
(2019) · The Springer Series on Challenges in Machine Learning · doi:10.1007/978-3-030-05318-5 · Cited by 1,485
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_19 · Cited by 1,415
“This factorization is similar in spirit to the depth-4 wise separable convolutions used in [12,13,14], except that we apply the idea to the temporal dimension instead of the feature dimension.”
MethodDeep face recognition: A survey
Wang, M., & Deng, W. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.10.081 · Cited by 1,466
Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs
Ding, X., Zhang, X., Han, J., & Ding, G. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01166 · Cited by 1,447
“We continue to evaluate large kernels on RepLKNet via fixing B = [2 , 2 , 18 , 2] , C = [128 , 256 , 512 , 1024] , varying K and observing the performance of both classification and semantic segmentation.”
BackgroundMethodAMC: AutoML for Model Compression and Acceleration on Mobile Devices
He, Y., Lin, J., Liu, Z., Wang, H., Li, L.-J., & Han, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_48 · Cited by 1,400
“NAS [57] aims to search the transferable network blocks, and its performance surpasses many manually designed architectures [47, 21, 9].”
BackgroundA Survey of Deep Learning-Based Object Detection
Jiao, L., Zhang, F., Liu, F., Yang, S., Li, L., Feng, Z., & Qu, R. (2019) · IEEE Access · doi:10.1109/access.2019.2939201 · Cited by 1,323
MetaFormer is Actually What You Need for Vision
Yu, W., Luo, M., Zhou, P., Si, C., Zhou, Y., Wang, X., Feng, J., & Yan, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01055 · Cited by 1,255
“8 Pooling → Depthwise Convolution [9, 37] 11.”
MethodMulti-Label Image Recognition With Graph Convolutional Networks
Chen, Z.-M., Wei, X.-S., Wang, P., & Guo, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00532 · Cited by 1,261
“The performance of image classification has recently witnessed a rapid progress due to the establishment of large-scale hand-labeled datasets such as ImageNet [4], MSCOCO [20] and PASCAL VOC [5], and the fast development of deep convolutional networks [10, 11, 35, 3, 32].”
BackgroundTransformers in medical imaging: A survey
Shamshad, F., Khan, S., Zamir, S. W., Khan, M. H., Hayat, M., Khan, F. S., & Fu, H. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102802 · Cited by 1,296
Deep learning for cellular image analysis
Moen, E., Bannon, D., Kudo, T., Graf, W., Covert, M., & Van Valen, D. (2019) · Nature Methods · doi:10.1038/s41592-019-0403-1 · Cited by 1,225
“…e , Separable convolutions perform the convolution operation on each channel separately, which reduces the computing power while preserving accuracy 156,157 . f , Residual networks learn the identity mapping plus a small residual and enable the construction of very deep networks 68 . g , Dense…”
BackgroundCoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images
Khan, A. I., Shah, J. L., & Bhat, M. M. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105581 · Cited by 1,312
“It is based on Xception CNN architecture [19] .”
3D MRI Brain Tumor Segmentation Using Autoencoder Regularization
Myronenko, A. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-11726-9_28 · Cited by 1,283
Deepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237
Vision Transformers for Single Image Dehazing
Song, Y., He, Z., Qian, H., & Du, X. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3256763 · Cited by 1,198
“Uformer [60] uses Swin Transformer blocks to build a U-Net-like network and inserted depth-wise convolution (DWConv) [61] in the feed-forward network (FFN) like LocalViT [62].”
MethodDeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
Kupyn, O., Martyniuk, T., Wu, J., & Wang, Z. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00897 · Cited by 1,148
“To reduce the complexity further, we try another more aggressive option on top of DeblurGAN-v2 with MobileNet V2, by replacing all normal convolu-tions in the full network (including those not in backbone) with Depthwise Separable Convolutions [6].”
MethodSimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
Yang, L., Zhang, R., Li, L., & Xie, X. (2021) · International Conference on Machine Learning · Cited by 2,734
Convolutional neural network: a review of models, methodologies and applications to object detection
Dhillon, A., & Verma, G. K. (2020) · Progress in Artificial Intelligence · doi:10.1007/s13748-019-00203-0 · Cited by 1,119
“Xception architecture [108] from is the extended version of inception model, which is completely based on depthwise distinguishable convolutions, followed by pointwise convolution.”
BackgroundMobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Mehta, S., & Rastegari, M. (2021) · arXiv · doi:10.48550/arxiv.2110.02178 · Cited by 1,110
“Because this layer is computationally expensive, several factorization-based methods have been proposed to make it light-weight and mobile-friendly (e.g., Jin et al., 2014; Chollet, 2017; Mehta et al., 2020).”
BackgroundMethodOmni-Scale Feature Learning for Person Re-Identification
Zhou, K., Yang, Y., Cavallaro, A., & Xiang, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00380 · Cited by 1,005
“To reduce the number of parameters, we adopt the depth-wise separable convolutions [15, 5].”
BackgroundMethodDeep learning classifiers for hyperspectral imaging: A review
Paoletti, M. E., Haut, J. M., Plaza, J., & Plaza, A. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.09.006 · Cited by 1,073
“, 2017), whose architecture is suitable for onboard processing, maximizing the accuracy while taking into account restricted resources for an integrated application, • Xception (Chollet, 2017), based on inception networks, where the original modules have been replaced with depthwise separable convolutions in order to…”
BackgroundInternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01385 · Cited by 1,080
“To remedy this problem, we borrow the idea from the separable convolution [55] and detach the original convolution weights wk into depth-wise and point-wise parts, where the depth-wise part is responsible by the original location-aware modulation scalar mk, and the point-wise part is the shared projection weights w am…”
MethodStudy on artificial intelligence: The state of the art and future prospects
Zhang, C., & Lu, Y. (2021) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2021.100224 · Cited by 1,066
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Liu, C., Chen, L.-C., Schroff, F., Adam, H., Hua, W., Yuille, A. L., & Fei-Fei, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00017 · Cited by 1,025
“Our model is lagged behind the top-performing DeepLabv3+ [11] with Xception-65 as network backbone by 2 .”
MethodUsing deep transfer learning for image-based plant disease identification
Chen, J., Chen, J., Zhang, D., Sun, Y., & Nanehkaran, Y. A. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105393 · Cited by 1,052
Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues
Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58610-2_6 · Cited by 1,058
Deep Residual Learning for Image Recognition: A Survey
Shafiq, M., & Gu, Z. (2022) · Applied Sciences · doi:10.3390/app12188972 · Cited by 1,023
Big Transfer (BiT): General Visual Representation Learning
Kolesnikov, A., Beyer, L., Zhai, X., Puigcerver, J., Yung, J., Gelly, S., & Houlsby, N. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58558-7_29 · Cited by 1,039
“ion images and 21k classes organized by the WordNet hierarchy. Images may contain multiple labels. BiT-L is trained on the JFT-300M dataset [51,38,61]. This dataset is a newer version of that used in [18,8]. JFT-300M consists of around 300 million images with 1.26 labels per image on average. The labels are organized…”
MethodInfluentialBig Transfer (BiT): General Visual Representation Learning
Kolesnikov, A., Beyer, L., Zhai, X., Puigcerver, J., Yung, J., Gelly, S., & Houlsby, N. (2019) · arXiv · doi:10.48550/arxiv.1912.11370 · Cited by 1,039
“ion images and 21k classes organized by the WordNet hierarchy. Images may contain multiple labels. BiT-L is trained on the JFT-300M dataset [51,38,61]. This dataset is a newer version of that used in [18,8]. JFT-300M consists of around 300 million images with 1.26 labels per image on average. The labels are organized…”
MethodInfluentialESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., & Hajishirzi, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_34 · Cited by 1,029
Fast and Accurate Single Image Super-Resolution via Information Distillation Network
Hui, Z., Wang, X., & Gao, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00082 · Cited by 955
Per-Pixel Classification is Not All You Need for Semantic Segmentation
Cheng, B., Schwing, A. G., & Kirillov, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.06278 · Cited by 164
Multi-attentional Deepfake Detection
Zhao, H., Wei, T., Zhou, W., Zhang, W., Chen, D., & Yu, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00222 · Cited by 1,019
“EfficientNet-b4 is able to achieve comparable performance to XceptionNet [3] with only half FLOPs.”
BackgroundSegmentation-based deep-learning approach for surface-defect detection
Tabernik, D., Šela, S., Skvarč, J., & Skočaj, D. (2020) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-019-01476-x · Cited by 898
“The DeepLabv3+ used in these experiments was based on the Xception (Chollet 2017) architecture containing 65 convolutional layers, trained and evaluated on a single scale and using an output stride of 16.”
Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey
Deng, B. L., Li, G., Han, S., Shi, L., & Xie, Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.2976475 · Cited by 996
“(f) Depthwise-separable Conv [34]. that are much easier to train.”
BackgroundMethodFastai: A Layered API for Deep Learning
Howard, J., & Gugger, S. (2020) · Information · doi:10.3390/info11020108 · Cited by 971
“er can customise it to create architectures that include squeeze and excitation blocks [42], grouped convolutions such as in ResNext [43], depth-wise convolutions such as in the Xception architecture [44], widening factors such as in Wide ResNets [45], self-attention and symmetric self-attention functionality , custom…”
MethodMedia Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979
“However, experiments carried out in [178] clearly show that, in a supervised setting, very deep general-purpose networks [179], [180], [181], outperform forensics-oriented shallow CNNs, as well as methods based on”
BackgroundHAQ: Hardware-Aware Automated Quantization With Mixed Precision
Wang, K., Liu, Z., Lin, Y., Lin, J., & Han, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00881 · Cited by 978
“Both MobileNets are inspired from the depthwise separable convolutions [4] and replace the regular convolutions with the pointwise and depthwise convolutions: MobileNet-V1 stacks multiple “depthwise – pointwise” blocks repeatedly; while MobileNet-V2 uses the “pointwise – depthwise – pointwise” blocks as its basic buil…”
BackgroundMethodStand-Alone Self-Attention in Vision Models
Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., & Shlens, J. (2019) · arXiv · doi:10.48550/arxiv.1906.05909 · Cited by 977
“[53] also show improvements on image classification and achieve state-of-the-art results on video action recognition tasks with a variant of non-local means.”
BackgroundEfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention
Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., & Yuan, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01386 · Cited by 956
“Similar to group convolutions [10, 87], the cascaded group attention could save the Flops and parameters by h×, since the input and output channels in the QKV layers are reduced by h×.”
BackgroundMethodInfluentialPruning and quantization for deep neural network acceleration: A survey
Liang, T., Glossner, J., Wang, L., Shi, S., & Zhang, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.045 · Cited by 943
Integral Human Pose Regression
Sun, X., Xiao, B., Wei, F., Liang, S., & Wei, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_33 · Cited by 874
Convolutional neural networks in medical image understanding: a survey
Sarvamangala, D. R., & Kulkarni, R. V. (2022) · Evolutionary Intelligence · doi:10.1007/s12065-020-00540-3 · Cited by 917
COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images
Hemdan, E. E., Shouman, M. A., & Karar, M. E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11055 · Cited by 913
“F) Xception: The architecture of Xception model is a linear stack of depth wise separable convolution layers with residual connections to easily define and modify the deep network architecture [40].”
BackgroundSlim-neck by GSConv: a lightweight-design for real-time detector architectures
Li, H., Li, J., Wei, H., Liu, Z., Zhan, Z., & Ren, Q. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-024-01436-6 · Cited by 886
CondenseNet: An Efficient DenseNet Using Learned Group Convolutions
Huang, G., Liu, S., Maaten, L. V. D., & Weinberger, K. Q. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00291 · Cited by 904
Gated Context Aggregation Network for Image Dehazing and Deraining
Chen, D., He, M., Fan, Q., Liao, J., Zhang, L., Hou, D., Yuan, L., & Hua, G. (2019) · 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2019.00151 · Cited by 809
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.