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 701–800 of 1,227
Cao, Y., Xu, J., Lin, S. C.-F., Wei, F., & Hu, H. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3047209 · Cited by 196
Ghaderzadeh, M., Aria, M., Hosseini, A., Asadi, F., Bashash, D., & Abolghasemi, H. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22753 · Cited by 190
Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild
Fard, A. P., & Mahoor, M. H. (2022) · IEEE Access · doi:10.1109/access.2022.3156598 · Cited by 157
Nafisah, S. I., & Muhammad, G. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07258-6 · Cited by 194
“In [29], the experiment was solely focused on image classification.”
InfluentialSahu, A., Das, P. K., & Meher, S. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104292 · Cited by 182
Zhou, T., Wang, W., Liang, Z., & Shen, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00572 · Cited by 156
“We see that both “Ours-FFIW10K” and “Xception-c40-FFIW10K” outperform their alternatives, i.e., “Ours-FF++” and “Xceptionc40-FF++”, which are trained on FF++ train.”
InfluentialFER-net: facial expression recognition using deep neural net
Karnati, M., Seal, A., Krejcar, O., & Yazidi, A. (2021) · Neural Computing and Applications · doi:10.1007/s00521-020-05676-y · Cited by 167
Domain General Face Forgery Detection by Learning to Weight
Sun, K., Liu, H., Ye, Q., Gao, Y., Liu, J., Shao, L., & Ji, R. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i3.16367 · Cited by 155
“Another direction is to use a generative model ( i.e., auto-encoder) to learn a latent embedding and map both the source domain and the target domain to the same space (Glorot, Bordes, and Bengio 2011; Chen et al. 2012).”
BackgroundA review of deep learning-based detection methods for COVID-19
Subramanian, N., Elharrouss, O., Al-Maadeed, S. A., & Chowdhury, M. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105233 · Cited by 174
“Xception [34] architectures are similar to the Inception family, where inception blockswith depthwise separable convolutional layers are used.”
Lightweight object detection algorithm for robots with improved YOLOv5
Liu, G., Hu, Y., Chen, Z., Guo, J., & Ni, P. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106217 · Cited by 176
Unsupervised Data AugmentationPreprint
Xie, Q., Dai, Z., Hovy, E. H., Luong, M.-T., & Le, Q. V. (2019) · arXiv (Cornell University) · Cited by 166
Modality-Specific Deep Learning Model Ensembles Toward Improving TB Detection in Chest Radiographs
Rajaraman, S., & Antani, S. (2020) · IEEE Access · doi:10.1109/access.2020.2971257 · Cited by 163
“The performance of the following CNNs are evaluated toward the task of detecting TB in CXRs: (a) customized CNN; (b) VGG-16; (c) Inception-V3 [21]; (d) InceptionResNet-V2 [21]; (e) Xception [27]; and (f) DenseNet-121 [28].”
BackgroundMethodVibration-based damage detection for bridges by deep convolutional denoising autoencoder
Shang, Z., Sun, L., Xia, Y., & We, Z. (2020) · Structural Health Monitoring · doi:10.1177/1475921720942836 · Cited by 166
“Separable convolutional layers 63 that perform convolution for each dimension may be developed to solve the problem.”
BackgroundCollaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration
Yang, Z., Wei, Y., & Yang, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3081597 · Cited by 198
GANSER: A Self-Supervised Data Augmentation Framework for EEG-Based Emotion Recognition
Zhang, Z., Liu, Y., & Zhong, S.-H. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3170369 · Cited by 178
“Then, because the recognition of specific emotions is only related to local patterns of spatial features or temporal features, we introduce a separable convolutional layer [37] to decouple the modeling of the spatiotemporal information.”
BackgroundAn investigation of XGBoost-based algorithm for breast cancer classification
Liew, X. Y., Hameed, N., & Clos, J. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100154 · Cited by 221
Wang, X., Yi, J., Guo, J., Song, Y., Lyu, J., Xu, J., Yan, W., Zhao, J., Cai, Q., & Min, H. (2022) · Remote Sensing · doi:10.3390/rs14215423 · Cited by 196
Live Face De-Identification in Video
Gafni, O., Wolf, L., & Taigman, Y. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00947 · Cited by 193
“The encoder is composed of a convolutional layer, followed by five strided, depth-wise separable [6] convolutions with instance normalization [48].”
A deep learning radiomics model for preoperative grading in meningioma
Zhu, Y., Man, C., Gong, L., Dong, D., Yu, X., Wang, S., Fang, M., Wang, S., Fang, X., Chen, X., et al. (2019) · European Journal of Radiology · doi:10.1016/j.ejrad.2019.04.022 · Cited by 159
Image-based defect detection in lithium-ion battery electrode using convolutional neural networks
Badmos, O., Kopp, A., Bernthaler, T., & Schneider, G. (2019) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-019-01484-x · Cited by 173
Multiscale Residual Network With Mixed Depthwise Convolution for Hyperspectral Image Classification
Gao, H., Yang, Y., Li, C., Gao, L., & Zhang, B. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3008286 · Cited by 165
“First, to reduce the training parameters and speed up the classification process, we adopt the depthwise separable convolution (DSC) [42] to design a lightweight CNN for HSI classification.”
MethodWhite Blood Cells Image Classification Using Deep Learning with Canonical Correlation Analysis
Patil, A., Patil, M. D., & Birajdar, G. K. (2020) · IRBM · doi:10.1016/j.irbm.2020.08.005 · Cited by 159
Convolutional neural network ensemble for Parkinson's disease detection from voice recordings
Hireš, M., Gazda, M., Drotár, P., Pah, N. D., Motin, M. A., & Kumar, D. K. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.105021 · Cited by 153
On the Automatic Detection and Classification of Skin Cancer Using Deep Transfer Learning
Fraiwan, M., & Faouri, E. (2022) · Sensors · doi:10.3390/s22134963 · Cited by 180
“These were: SqueezeNet [33], GoogLeNet [34], Inceptionv3 [35], DenseNet-201 [36], MobileNetv2, ResNet18, Rest-Net50, ResNet101, Xception [37], Inception-ResNet, ShuffleNet [38], DarkNet-53 [39], and EfficientNet-b0 [40].”
Fast vehicle detection algorithm in traffic scene based on improved SSD
Chen, Z., Guo, H., Yang, J., Jiao, H., Feng, Z., Chen, L., & Gao, T. (2022) · Measurement · doi:10.1016/j.measurement.2022.111655 · Cited by 171
ÇELİK, M., & İnik, Ö. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122159 · Cited by 181
A robust deep learning framework for multiclass skin cancer classification
Özdemir, B., & Paçal, İ. (2025) · Scientific Reports · doi:10.1038/s41598-025-89230-7 · Cited by 206
Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
Mukhoti, J., & Gal, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.12709 · Cited by 138
Identification of Apple Tree Leaf Diseases Based on Deep Learning Models
Chao, X., Sun, G., Hongke, Z., Li, M., & He, D. (2020) · Symmetry · doi:10.3390/sym12071065 · Cited by 166
Identifying crop water stress using deep learning models
Chandel, N. S., Chakraborty, S. K., Rajwade, Y. A., Dubey, K., Tiwari, M. K., & Jat, D. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05325-4 · Cited by 170
ZigZag: Enlarging Joint Architecture-Mapping Design Space Exploration for DNN Accelerators
Mei, L., Houshmand, P., Jain, V., Giraldo, J. S. P., & Verhelst, M. (2021) · IEEE Transactions on Computers · doi:10.1109/tc.2021.3059962 · Cited by 248
Fire-Net: A Deep Learning Framework for Active Forest Fire Detection
Seydi, S. T., Saeidi, V., Kalantar, B., Ueda, N., & Halin, A. B. A. (2022) · Journal of Sensors · doi:10.1155/2022/8044390 · Cited by 198
Amin, S. U., Hussain, A., Kim, B., & Seo, S. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120391 · Cited by 198
DeeperLab: Single-Shot Image Parser
Yang, T.-J., Collins, M. D., Zhu, Y., Hwang, J.-J., Liu, T., Zhang, X., Sze, V., Papandreou, G., & Chen, L.-C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.05093 · Cited by 135
StegNet: Mega Image Steganography Capacity with Deep Convolutional Network
Wu, P., Yang, Y., & Li, X. (2018) · Future Internet · doi:10.3390/fi10060054 · Cited by 172
“ble Convolution with Residual Block Our work adopt the state of the art neural network structure, the skip connections in Highway Network [38], ResNet [39] and ResNeXt [40], and separable convolution [41] together to form the basic building block “SCR”. The idea behind separable convolution [41] originated from Google…”
MethodEfficient Facial Feature Learning with Wide Ensemble-Based Convolutional Neural Networks
Siqueira, H. L., Magg, S., & Wermter, S. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6037 · Cited by 175
Ma, H., Liu, Y., Ren, Y., & Yu, J. (2019) · Remote Sensing · doi:10.3390/rs12010044 · Cited by 174
“Shuffle et v2 is a lightweight classification network proposed in 2018, which introduced the idea of depth-wise convolution [28] and group convolution.”
BackgroundKhalifa, N. E. M., Taha, M. H. N., Hassanien, A. E., & Elghamrawy, S. M. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-20601-6_22 · Cited by 201
Notice of Retraction: AI Techniques for COVID-19
Hussain, A. A., Bouachir, O., Al-Turjman, F., & Aloqaily, M. (2020) · IEEE Access · doi:10.1109/access.2020.3007939 · Cited by 166
RetractedYang, J., Wang, X., Wang, R., & Wang, H. (2020) · Geoderma · doi:10.1016/j.geoderma.2020.114616 · Cited by 166
The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances
Du, H., Shi, H., Zeng, D., Zhang, X.-P. S., & Mei, T. (2022) · ACM Computing Surveys · doi:10.1145/3507902 · Cited by 203
“alized architectures include the modified or ensemble designs oriented to face recognition. 5.1.1 General architectures. With the advanced feature learning ability of deep convolution neural networks [33, 65, 78, 85, 115, 203, 221, 238], deep face representation has made great progress. Among them, AlexNet [115] obtai…”
BackgroundResultInfluentialSlideGraph + : Whole slide image level graphs to predict HER2 status in breast cancer
Lu, W., Toss, M. S., Dawood, M., Rakha, E. A., Rajpoot, N., & Minhas, F. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102486 · Cited by 172
Wang, Z., Wang, J., Yang, K., Wang, L., Su, F., & Chen, X. (2021) · Computers & Geosciences · doi:10.1016/j.cageo.2021.104969 · Cited by 163
Rahman, K. K. M., & Subashini, M. M. (2022) · Brain Sciences · doi:10.3390/brainsci12010094 · Cited by 175
RetractedSurvey of Optimization Algorithms in Modern Neural Networks
Abdulkadirov, R. I., Lyakhov, P. A., & Nagornov, N. N. (2023) · Mathematics · doi:10.3390/math11112466 · Cited by 220
“In the case of DenseNet [122], Xception [123], ShuffleNet [124], and GhostNet [125], it is necessary to use advanced Adam-type algorithms, such as DiffGrad, Yogi, AdaBelief, AdaBound, AdamInject, and AdaPNM.”
Fake Face Detection Methods: Can They Be Generalized?
Khodabakhsh, A., Ramachandra, R., Raja, K., Wasnik, P., & Busch, C. (2018) · 2018 International Conference of the Biometrics Special Interest Group (BIOSIG) · doi:10.23919/biosig.2018.8553251 · Cited by 151
“The selection of CNN architectures AlexNet [7], VGG19 [8], ResNet50 [9], Xception [10], and GoogLeNet/Inceptionv3 [11] is based on the recent works demonstrating very high performance for various tasks.”
BackgroundMethodHydra: An Ensemble of Convolutional Neural Networks for Geospatial Land Classification
Minetto, R., Segundo, M. P., & Sarkar, S. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2906883 · Cited by 162
“They were chosen after experimenting with them and other architectures: VGG-16 [17], VGG-19 [17], Inception V3 [25], and Xception [26].”
Self-Supervised Feature Learning via Exploiting Multi-Modal Data for Retinal Disease Diagnosis
Li, X., Jia, M., Islam, M. T., Yu, L., & Xing, L. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3008871 · Cited by 150
Ghostnet for Hyperspectral Image Classification
Paoletti, M. E., Haut, J. M., Pereira, N. S. A., Plaza, J., & Plaza, A. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3050257 · Cited by 156
“Inspired by previous models that attempt to reduce both the number of parameters and the computational cost associated with the convolution layer [32], [33], the proposed deep convolutional network exploits the advantages provided by the ghost module [34], which divides the standard convolution layer into two steps.”
MethodArtificial intelligence for breast cancer analysis: Trends & directions
Shah, S. M., Khan, R. A., Arif, S., & Sajid, U. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105221 · Cited by 144
A New Deep Hybrid Boosted and Ensemble Learning-Based Brain Tumor Analysis Using MRI
Zahoor, M. M., Qureshi, S. A., Bibi, S., Khan, S. H., Khan, A., Ghafoor, U., & Bhutta, M. R. (2022) · Sensors · doi:10.3390/s22072726 · Cited by 192
“Employed CNN models includes: i-VGG-16 [22], ii-VGG-19 [22], iii-SqueezeNet [23], iv-GoogleNet [24], v-ResNet-18 [25], vi-ResNet-50 [25], vii-XceptionNet [26], vii-”
Skin cancer diagnosis based on deep transfer learning and sparrow search algorithm
Balaha, H. M., & Hassan, A. E.-S. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07762-9 · Cited by 182
“Many pre-trained CNN models are available to be used such as VGG16 [118], ResNet [58], MobileNet [62], Xception [34], NASNet [141], and DenseNet [63].”
MethodMIO-TCD: A New Benchmark Dataset for Vehicle Classification and Localization
(2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2848705 · Cited by 149
Machine-learning based vulnerability analysis of existing buildings
Ruggieri, S., Cardellicchio, A., Leggieri, V., & Uva, G. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.103936 · Cited by 155
Wang, Y., Luo, Q., Xie, H., Li, Q., & Sun, G. (2022) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2022.107529 · Cited by 149
Bouguettaya, A., Zarzour, H., Kechida, A., & Taberkit, A. M. (2022) · Cluster Computing · doi:10.1007/s10586-022-03627-x · Cited by 149
“[34], VGG-19 Simonyan and Zisserman [67], and Xception Chollet [22].”
BackgroundHRTransNet: HRFormer-Driven Two-Modality Salient Object Detection
Tang, B., Liu, Z., Tan, Y., & He, Q. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3202563 · Cited by 183
Zhuang, W., Chu, Q., Tan, Z., Liu, Q., Yuan, H., Miao, C., Luo, Z., & Yu, N. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20065-6_23 · Cited by 225
Single Image Depth Estimation Trained via Depth From Defocus Cues
Gur, S., & Wolf, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00787 · Cited by 139
“The PSF layer we employ can be seen as a particular case of the locally connected layers of [34], with a few differences: first, in the PSF layer, the same operator is applied across all channels, while in the locally-connected layer, as well as in conventional layers (excluding depthconvolution [6]), the local operat…”
MethodAdaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology
Tokunaga, H., Teramoto, Y., Yoshizawa, A., & Bise, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01288 · Cited by 141
“We modi-fied Xception [11] (developed by Google) for classification by replacing the fully connected (FC) layers with global average pooling, a 3-class FC layer, and a sigmoid activation function to output three weights and fine-tuned the network by using the trained parameters for 1000-class…”
MethodMulti-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition
Luvizon, D. C., Picard, D., & Tabia, H. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2976014 · Cited by 205
ShelfNet for Fast Semantic Segmentation
Zhuang, J., Yang, J., Gu, L., & Dvornek, N. C. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00113 · Cited by 179
Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes
Dong, G., Yan, Y., Shen, C., & Wang, H. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2980426 · Cited by 164
Deep Learning for Automatic Pneumonia Detection
Gabruseva, T., Poplavskiy, D., & Kalinin, A. A. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00183 · Cited by 172
Learning with Privileged Information for Efficient Image Super-Resolution
Lee, W.-K., Lee, J., Kim, D., & Ham, B. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58586-0_28 · Cited by 175
StNet: Local and Global Spatial-Temporal Modeling for Action Recognition
He, D., Zhou, Z., Gan, C., Li, F., Liu, X., Li, Y., Wang, L., & Wen, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018401 · Cited by 143
Roslidar, R., Rahman, A., Muharar, R., Syahputra, M. R., Arnia, F., Syukri, M., Pradhan, B., & Munadi, K. (2020) · IEEE Access · doi:10.1109/access.2020.3004056 · Cited by 169
“[131] F. Chollet, ‘‘Xception: Deep learning with depthwise separable convolutions,’’ in Proc.”
MethodKarar, M. E., Hemdan, E. E., & Shouman, M. A. (2020) · Complex & Intelligent Systems · doi:10.1007/s40747-020-00199-4 · Cited by 159
“It has been developed based on the architecture of pre-trained Xception model [44], resulting an overall accuracy of 89.”
MethodLightweight deep learning models for detecting COVID-19 from chest X-ray images
Karakanis, S., & Leontidis, G. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.104181 · Cited by 154
MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
Gao, G., Xu, G., Yu, Y., Xie, J., Yang, J. J., & Yue, D. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3098355 · Cited by 158
“Xception [16] and MobileNet [17] applied depth-wise separable convolution, where each input channel and each filter kernel is divided into”
MethodWINNet: Wavelet-Inspired Invertible Network for Image Denoising
Huang, J., & Dragotti, P. L. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3184845 · Cited by 181
“Separable Convolution: A depth-wise separable convolution layer [49] consists of a depth-wise convolution layer and a 1 × 1 convolution layer (shown in Fig.”
BackgroundMethodLu, W., Chen, J., & Xue, F. (2021) · Resources Conservation and Recycling · doi:10.1016/j.resconrec.2021.106022 · Cited by 172
On the Performance of Deep Transfer Learning Networks for Brain Tumor Detection Using MR Images
Ahmad, S., & Choudhury, P. K. (2022) · IEEE Access · doi:10.1109/access.2022.3179376 · Cited by 164
Paçal, İ. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111482 · Cited by 169
Deep Transfer Learning Models for Medical Diabetic Retinopathy Detection
Khalifa, N. E. M., Loey, M., Taha, M. H. N., & Mohamed, H. (2019) · Acta Informatica Medica · doi:10.5455/aim.2019.27.327-332 · Cited by 168
Rodrigues, D. D. A., Ivo, R. F., Satapathy, S. C., Wang, S., Hemanth, D. J., & Filho, P. P. R. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.05.019 · Cited by 161
Borra, D., Fantozzi, S., & Magosso, E. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.05.032 · Cited by 145
A Survey of Computer Vision Methods for 2D Object Detection from Unmanned Aerial Vehicles
Cazzato, D., Cimarelli, C., Sánchez-López, J. L., Voos, H., & Leo, M. (2020) · Journal of Imaging · doi:10.3390/jimaging6080078 · Cited by 175
Lung Nodule Classification via Deep Transfer Learning in CT Lung Images
da Nóbrega, R. V. M., Peixoto, S. A., da Silva, S. P. P., & Filho, P. P. R. (2018) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2018.00050 · Cited by 163
Liu, D., Liu, F., Xie, X., Su, L., Liu, M., Xie, X., Kuang, M., Huang, G., Wang, Y., Zhou, H., et al. (2020) · European Radiology · doi:10.1007/s00330-019-06553-6 · Cited by 148
Sahlol, A. T., Elaziz, M. A., Jamal, A. T., Damaševičius, R., & Hassan, O. F. (2020) · Symmetry · doi:10.3390/sym12071146 · Cited by 168
“The examples of pre-trained neural networks are VGGNet [34], ResNet (GoogLeNet) [35], Nasnet [36], Mobilenet [37], Inception [38] and Xception [39].”
Sudo RM -RF: Efficient Networks for Universal Audio Source Separation
Tzinis, E., Wang, Z., & Smaragdis, P. (2020) · Machine learning for signal processing ... · doi:10.1109/mlsp49062.2020.9231900 · Cited by 215
“In most of the studies where efficient architectures are introduced [11, 10, 12, 13] authors are mainly concerned with the total number of trainable parameters of the network.”
BackgroundMethodMotionSqueeze: Neural Motion Feature Learning for Video Understanding
Kwon, H., Kim, M., Kwak, S., & Cho, M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58517-4_21 · Cited by 192
Das, P. K., Diya, V., Meher, S., Panda, R., & Abraham, A. (2022) · IEEE Access · doi:10.1109/access.2022.3196037 · Cited by 173
TINYCD: a (not so) deep learning model for change detection
Codegoni, A., Lombardi, G., & Ferrari, A. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-08122-3 · Cited by 181
Remote Sensing Image Scene Classification Based on an Enhanced Attention Module
Zhao, Z., Li, J., Luo, Z., Li, J., & Chen, C. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.3011405 · Cited by 152
Image Preprocessing in Classification and Identification of Diabetic Eye Diseases
Sarki, R., Ahmed, K. E. U., Wang, H., Zhang, Y., Ma, J., & Wang, K. (2021) · Data Science and Engineering · doi:10.1007/s41019-021-00167-z · Cited by 180
Multi-level attention network: application to brain tumor classification
Shaik, N. S., & Cherukuri, T. K. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-02022-0 · Cited by 171
“[14] with depth-wise and point-wise convolution operations that enables modeling and learning rich feature representations by applying spatial convolution on each channel independently.”
BackgroundLiu, Z., Abeyrathna, R. M. R. D., Sampurno, R. M., Nakaguchi, V. M., & Ahamed, T. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109118 · Cited by 168
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
Nekrasov, V., Dharmasiri, T., Spek, A., Drummond, T., Shen, C., & Reid, I. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8794220 · Cited by 138
“grouped convolution with the number of groups being equal to the number of input channels) [42].”
BackgroundBenchmarking the Robustness of Semantic Segmentation Models
Kamann, C., & Rother, C. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00885 · Cited by 213
Kattenborn, T., Eichel, J., Wiser, S. K., Burrows, L., Fassnacht, F. E., & Schmidtlein, S. (2020) · Remote Sensing in Ecology and Conservation · doi:10.1002/rse2.146 · Cited by 159
“We setup the CNN using Depthwise Seper-able Convolutions (also known as Xception, Chollet 2017).”
MethodTang, Y., Teng, Q., Zhang, L., Min, F., & He, J. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3015521 · Cited by 143
“Based on the idea, Xception [16], MobileNet [17], Shufflenet [18] and ResNeXt [19] have achieved the state-of-the-art performance.”
BackgroundMethodTufail, A. B., Ma, Y.-K., Kaabar, M. K. A., Martínez, F., Junejo, A. R., Ullah, I., & Khan, R. (2021) · Computational and Mathematical Methods in Medicine · doi:10.1155/2021/9025470 · Cited by 143
Medical image segmentation with 3D convolutional neural networks: A survey
Niyas, S., Pawan, S. J., Kumar, M. A., & Rajan, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.065 · Cited by 171
Ojo, M. O., & Zahid, A. (2022) · Sensors · doi:10.3390/s22207965 · Cited by 192
“Other backbone network structures include Xception [112] with different layers of 65 and 71, EfficientNet [113], and PRPNet [55].”
BackgroundMaqsood, S., & Damaševičius, R. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.022 · Cited by 164
Memari, M., Shakya, P., Shekaramiz, M., Seibi, A. C., & Masoum, M. A. S. (2024) · IEEE Access · doi:10.1109/access.2024.3371493 · Cited by 179
Cheng, J., Deng, C., Su, Y., An, Z., & Wang, Q. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.03.012 · Cited by 179
Vision-based Fight Detection from Surveillance Cameras
Aktı, Ş., Tataroglu, G. A., & Ekenel, H. K. (2019) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2019.8936070 · Cited by 171
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.