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 501–600 of 1,227
Depthwise Convolution Is All You Need for Learning Multiple Visual Domains
Guo, Y., Li, Y., Wang, L., & Rosing, T. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018368 · Cited by 190
A CNN-based methodology for breast cancer diagnosis using thermal images
Zuluaga-Gomez, J., Al Masry, Z., Benaggoune, K., Meraghni, S., & Zerhouni, N. (2021) · Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization · doi:10.1080/21681163.2020.1824685 · Cited by 201
“ew cases will come. Under that proposed training framework, we have tested several state-of-the-art CNN architectures: ResNet [47], SeResNet [48], VGG16, Inception, InceptionResNetV2 [49]and Xception [50]. Afterward, we made a comparison between the baseline and the state-ofthe-art models, finding that simpler CNN mode…”
MethodInfluentialMs RED: A novel multi-scale residual encoding and decoding network for skin lesion segmentation
Dai, D., Dong, C., Xu, S., Yan, Q., Li, Z., Zhang, C., & Luo, N. (2022) · Medical Image Analysis · doi:10.1016/j.media.2021.102293 · Cited by 203
Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples
Hussain, S., Neekhara, P., Jere, M., Koushanfar, F., & McAuley, J. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00339 · Cited by 204
“In our work, we consider two victim CNN classifiers: XceptionNet [13] and MesoNet [1].”
MethodInfluentialDepthwise Separable Convolution Neural Network for High-Speed SAR Ship Detection
Zhang, T., Zhang, X., Shi, J., & Wei, S. (2019) · Remote Sensing · doi:10.3390/rs11212483 · Cited by 203
“DS-CNN was first proposed by L. Sifre in 2014 [45], which has been successfully applied to Xception [46] and MobileNet [44].”
BackgroundMethodInfluentialDeep Learning for Lung Cancer Nodules Detection and Classification in CT Scans
Riquelme, D., & Akhloufi, M. (2020) · AI · doi:10.3390/ai1010003 · Cited by 202
“Among them Residual Networks (ResNets) [9], Inception [10,11], Xception [12] or Dense Networks [13,14].”
BackgroundFarag, M. M., Fouad, M., & Abdel-Hamid, A. T. (2022) · IEEE Access · doi:10.1109/access.2022.3165193 · Cited by 198
“Kassani et al. [25] used a Multi-Layer Perceptron (MLP) as a classification head on top of the modified Xception network [26] by concatenating different feature maps from different convolutional layers.”
MethodA Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends
Younesi, A., Ansari, M., Fazli, M., Ejlali, A., Shafique, M., & Henkel, J. (2024) · IEEE Access · doi:10.1109/access.2024.3376441 · Cited by 197
“Overall, these libraries and frameworks represent the forefront of open-source tools transforming CV through deep learning.”
Background(2020) · arXiv (Cornell University) · Cited by 204
Gaudet, C. J., & Maida, A. S. (2018) · 2018 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489651 · Cited by 187
Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems
Gobieski, G., Lucia, B., & Beckmann, N. (2019) · Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/3297858.3304011 · Cited by 203
“t need full-precision floating-point and reducing weight precision [22,31] reduces storage and computation costs. Additional reductions in storage and computation comes from factoring DNN computations [9,14,40,59,68,70,71]. Despite these efforts, power consumption remains orders of magnitude too high for energy-harvest…”
BackgroundMethodA fuzzy rank-based ensemble of CNN models for classification of cervical cytology
Manna, A., Kundu, R., Kaplun, D., Sinitca, A., & Sarkar, R. (2021) · Scientific Reports · doi:10.1038/s41598-021-93783-8 · Cited by 203
A classification of MRI brain tumor based on two stage feature level ensemble of deep CNN models
Aurna, N. F., Yousuf, M. A., Taher, K. A., Azad, A. K. M., & Moni, M. A. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105539 · Cited by 203
Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection
Tan, C., Zhao, Y., Wei, S., Gu, G., & Wei, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01165 · Cited by 203
“Rossler et al. [37] introduce a largescale manipulated face dataset FaceForensics++ and adopt Xception [7] as detector to identify the fake images with compression.”
MethodDSNet: Automatic dermoscopic skin lesion segmentation
Hasan, M. K., Dahal, L., Samarakoon, P. N., Tushar, F. I., & Martí, R. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103738 · Cited by 200
Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
Lei, H., Akhtar, N., & Mian, A. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2983410 · Cited by 202
Space-Time-Separable Graph Convolutional Network for Pose Forecasting
Sofianos, T., Sampieri, A., Franco, L., & Galasso, F. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01102 · Cited by 195
Rethinking Spatiotemporal Feature Learning For Video Understanding.
Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. P. (2017) · Cited by 227
Multi-Label Classification of Fundus Images With EfficientNet
Wang, J., Yang, L., Huo, Z., He, W., & Luo, J. (2020) · IEEE Access · doi:10.1109/access.2020.3040275 · Cited by 199
Machine Learning With Neuromorphic Photonics
de Lima, T. F., Peng, H.-T., Tait, A. N., Nahmias, M. A., Miller, H. B., Shastri, B. J., & Prucnal, P. R. (2019) · Journal of Lightwave Technology · doi:10.1109/jlt.2019.2903474 · Cited by 200
Liu, B., Tan, C., Li, S., He, J., & Wang, H. (2020) · IEEE Access · doi:10.1109/access.2020.2998839 · Cited by 200
“These prevailing models are selected to show the robustness of the proposed data augmentation method as their various characteristics: AlexNet and VGGNet are composed of plain convolutional neural networks with a number of layers; ResNet and DenseNet are the typical models that implement skip connections by different…”
MethodMachine learning toward advanced energy storage devices and systems
Gao, T., & Lu, W. (2021) · iScience · doi:10.1016/j.isci.2020.101936 · Cited by 199
“The models used in the research include traditional CNNmodels (Baseline model, Sigmoid model, and Softmax model) trained by limited battery data and TL CNN models (pretrained VGG19 (Simonyan and Zisserman, 2014), inception V3 (Szegedy et al., 2016), and Xception (Chollet, 2017), with a new fully connected layer added…”
MethodRethinking on Multi-Stage Networks for Human Pose EstimationPreprint
Li, W., Wang, Z., Yin, B., Peng, Q., Du, Y., Xiao, T., Yu, G., Lu, H., Wei, Y., & Sun, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.00148 · Cited by 333
“We conduct more experiments on ResNet-18 and Xception [9] XCP) and a small one (S-XCP).”
MethodSemantic Correlation Promoted Shape-Variant Context for Segmentation
Ding, H., Jiang, X., Shuai, B., Liu, A. Q., & Wang, G. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00909 · Cited by 188
Shevchik, S. A., Masinelli, G., Kenel, C., Leinenbach, C., & Wasmer, K. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2910524 · Cited by 197
Li, G., Huang, Y., Chen, Z., Chesser, G. D., Purswell, J. L., Linhoss, J., & Zhao, Y. (2021) · Sensors · doi:10.3390/s21041492 · Cited by 197
“Xception [162] Extreme inception module, depthwise separable convolution GitHub [163] (TensorFlow) [120]”
BackgroundActivate or Not: Learning Customized Activation
Ma, N., Zhang, X., Liu, M., & Sun, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00794 · Cited by 181
“Dynamic network Standard CNNs [44, 16, 47, 59, 6, 19, 43, 18] share the same network structure and convolution kernels for all the samples, while conditional (or dynamic) CNNs [29, 32, 54, 58, 26, 34] use dynamic kernels, widths, or depths conditioned on the input samples, obtaining remarkably gains in accuracy.”
BackgroundCombating disinformation in a social media age
Shu, K., Bhattacharjee, A., Alatawi, F., Nazer, T. H., Ding, K., Karami, M., & Liu, H. (2020) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1385 · Cited by 198
“It was seen that, in the case of compressed images, even with an overall decline in the performance of all the detectors studied, XceptionNet (Chollet, 2017) gave quite accurate results.”
BackgroundResultChoi, S., Kim, J. T., & Choo, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00939 · Cited by 187
“0 DeepLabv3+ [8](’18)† Xception [11] 82.”
OC-FakeDect: Classifying Deepfakes Using One-class Variational Autoencoder
Khalid, H., & Woo, S. S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00336 · Cited by 197
“Table 2 summarizes the accuracy scores of all three OC models and the two-class low quality trained models such as MesoNet and XceptionNet across the five types of datasets.”
BackgroundInfluentialMundt, M., Majumder, S., Murali, S., Panetsos, P., & Ramesh, V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01145 · Cited by 169
“The allowed feature operations are convolutions with square filters of size 3 and 5, corresponding depth-wise separable convolutions [6], maxpooling and average-pooling with kernel size 3 × 3.”
MethodAlonso-Monsalve, S., Suárez-Cetrulo, A. L., Cervantes, A., & Quintana, D. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113250 · Cited by 195
“We would like to highlight that all the fil-466 ters from the convolutional layers have a horizontal shape (their shape467 is 1xK), allowing each kernel to work on a single time instant over468 multiple indicators, and thus preventing to perform convolutions that469 merge multiple time instants.470 • DNN: a custom dee…”
BackgroundInfluentialAhmad, S., Shakeel, I., Mehfuz, S., & Ahmad, J. (2023) · Computer Science Review · doi:10.1016/j.cosrev.2023.100568 · Cited by 197
Liu, P., Liu, X., Liu, M., Shi, Q., Yang, J., Xu, X., & Zhang, Y. (2019) · Remote Sensing · doi:10.3390/rs11070830 · Cited by 196
“1×1 convolution to fuse the output of each channel [50], as presented in Figure 3.”
BackgroundMethodInfluentialValan, M., Makonyi, K., Maki, A., Vondráček, D., & Ronquist, F. (2019) · Systematic Biology · doi:10.1093/sysbio/syz014 · Cited by 194
“VGG16 has a simpler structure compared to other current architectures, such as Microsofts ResNets (He et al. 2016) [17:17 23/9/2019 Sysbio-OP-SYSB190016.tex] Page: 881 876–895 or Google’s Inception v3 (Szegedy et al. 2016b), Inception v4 (Szegedy et al. 2016a), and Xception (Chollet 2016).”
MethodAkcay, S., & Breckon, T. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2021.108245 · Cited by 194
Capra, M., Bussolino, B., Marchisio, A., Shafique, M., Masera, G., & Martina, M. (2020) · Future Internet · doi:10.3390/fi12070113 · Cited by 195
S2-MLP: Spatial-Shift MLP Architecture for Vision
Yu, T., Li, X., Cai, Y., Sun, M., & Li, P. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv51458.2022.00367 · Cited by 195
Boroujeni, S. P. H., Razi, A., Khoshdel, S., Afghah, F., Coen, J. L., O’Neill, L., Fule, P., Watts, A., Kokolakis, N.-M. T., & Vamvoudakis, K. G. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102369 · Cited by 194
GhostNets on Heterogeneous Devices via Cheap Operations
Han, K., Wang, Y., Xu, C., Guo, J., Xu, C., Wu, E., & Tian, Q. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01575-y · Cited by 192
DPP-Net: Device-Aware Progressive Search for Pareto-Optimal Neural Architectures
Dong, J.-D., Cheng, A.-C., Juan, D.-C., Wei, W., & Sun, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_32 · Cited by 189
Bala, D., Hossain, M. S., Hossain, M. A., Abdullah, M. I., Rahman, M. M., Manavalan, B., Gu, N., Islam, M. S., & Huang, Z. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.02.022 · Cited by 191
Mou, L., & Zhu, X. X. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2841808 · Cited by 174
Road damage detection algorithm for improved YOLOv5
Guo, G., & Zhang, Z. (2022) · Scientific Reports · doi:10.1038/s41598-022-19674-8 · Cited by 191
Emotion recognition from unimodal to multimodal analysis: A review
Ezzameli, K., & Mahersia, H. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101847 · Cited by 187
SOD-YOLO: Small-Object-Detection Algorithm Based on Improved YOLOv8 for UAV Images
Li, Y., Li, Q., Pan, J., Zhou, Y., Zhu, H., Wei, H., & Liu, C. (2024) · Remote Sensing · doi:10.3390/rs16163057 · Cited by 187
Ghasemi, A., Hashtarkhani, S., Schwartz, D. L., & Shaban‐Nejad, A. (2024) · Cancer Innovation · doi:10.1002/cai2.136 · Cited by 193
Mehnatkesh, H., Jalali, S. M. J., Khosravi, A., & Nahavandi, S. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119087 · Cited by 191
A survey on deep learning for skin lesion segmentation
Mirikharaji, Z., Abhishek, K., Bissoto, A., Barata, C., Avila, S., Valle, E., Celebi, M. E., & Hamarneh, G. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102863 · Cited by 189
“Separable convolution: Separable convolution or depth-wise separable convolution (Chollet, 2017) is a spatial convolution operation that convolves each input channel with its corresponding kernel.”
BackgroundCountering Malicious DeepFakes: Survey, Battleground, and Horizon
Juefei-Xu, F., Wang, R., Huang, Y., Guo, Q., Ma, L., & Liu, Y. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01606-8 · Cited by 191
“W a n g ' 21 2017) with significant accuracy reduction on the public datasets (Wang et al., 2020e; Frank et al., 2020).”
BackgroundMethodInfluentialLearning Dynamic Routing for Semantic Segmentation
Li, Y., Song, L., Chen, Y., Li, Z., Zhang, X., Wang, X., & Sun, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00858 · Cited by 184
Li, Y., Chen, W., Zhang, Y., Tao, C., Xiao, R., & Tan, Y. (2020) · Remote Sensing of Environment · doi:10.1016/j.rse.2020.112045 · Cited by 191
Thangaraj, R., Anandamurugan, S., & Kaliappan, V. K. (2021) · Journal of Plant Diseases and Protection · doi:10.1007/s41348-020-00403-0 · Cited by 188
Dense extreme inception network for edge detection
Poma, X. S., Sappa, A. D., Ramos, P. R. H., & Akbarinia, A. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109461 · Cited by 216
“This inspired us to design an architecture similar to Xception [41] but with two parallel skip-connections that materialize on all the edge information computed across different layers.”
MethodAutomatic Design of Convolutional Neural Network for Hyperspectral Image Classification
Chen, Y., Zhu, K., Zhu, L., He, X., Ghamisi, P., & Benediktsson, J. A. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2910603 · Cited by 190
An Automatic Nucleus Segmentation and CNN Model based Classification Method of White Blood Cell
Banik, P. P., Saha, R., & Kim, K.-D. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113211 · Cited by 188
Fully Convolutional Networks for Panoptic Segmentation
Li, Y., Zhao, H., Qi, X., Wang, L., Li, Z., Sun, J., & Jia, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00028 · Cited by 182
“All results are compared with Res50 except DeeperLab [51] based on Xception-71 [7].”
ResultInfluentialWehbe, R. M., Sheng, J., Dutta, S., Chai, S., Dravid, A., Barutcu, S., Wu, Y., Cantrell, D. R., Xiao, N., Allen, B. D., et al. (2021) · Radiology · doi:10.1148/radiol.2020203511 · Cited by 190
Detection of sick broilers by digital image processing and deep learning
Zhuang, X., & Zhang, T. (2019) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2019.01.003 · Cited by 187
Semantic segmentation of agricultural images: A survey
Luo, Z., Yang, W., Yuan, Y., Gou, R., & Li, X. (2024) · Information Processing in Agriculture · doi:10.1016/j.inpa.2023.02.001 · Cited by 183
Multi-class classification of brain tumor types from MR images using EfficientNets
Zulfiqar, F., Ijaz Bajwa, U., & Mehmood, Y. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.104777 · Cited by 184
Gonzalez-Huitron, V., León-Borges, J. A., Rodriguez-Mata, A. E., Amabilis-Sosa, L. E., Ramírez-Pereda, B., & Rodriguez, H. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105951 · Cited by 186
Graphonomy: Universal Human Parsing via Graph Transfer Learning
Gong, K., Gao, Y., Liang, X., Shen, X., Wang, M., & Lin, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00763 · Cited by 182
“Following [3], we employ the Xception [7] pre-trained on COCO [31] as our network backbone and output stride = 16.”
MethodSkin Cancer Detection Using Deep Learning—A Review
Naqvi, M., Gilani, S. Q., Syed, T., Marques, O., & Kim, H.-C. (2023) · Diagnostics · doi:10.3390/diagnostics13111911 · Cited by 185
“Alenezi et al. [33] also trained SVM on features extracted using AlexNet, DarkNet19 [34], GoogleNet [25], SqueezeNet [35], Xception [36], and MobileNetV2 [37], with SVM giving the best accuracy of 96.15% and 97.15% on ISIC 2019 and ISIC 2020 with features extracted using ResNet-101 [20].”
MethodInfluentialYu, Y., Zhang, Y., Cheng, Z., Song, Z., & Tang, C. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107079 · Cited by 183
ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
Song, X., Wang, P., Zhou, D., Zhu, R., Guan, C., Dai, Y., Su, H., Li, H., & Yang, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00560 · Cited by 186
“We adopted the fully convolutional features from DeepLabv3 [5] with Xception65 [8] network and follow the same training policy.”
MethodAsad, M. H., & Bais, A. (2020) · Information Processing in Agriculture · doi:10.1016/j.inpa.2019.12.002 · Cited by 184
Wang, Z., Xiao, Y., Li, Y., Zhang, J., Lu, F., Hou, M., & Liu, X. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2020.107613 · Cited by 186
“JID: PR [m5G; August 29, 2020;23:46 ] based on state-of-the-art methods, such as fully convolutional neural networks (FCNNs) [6] , VGGNet [7] , ResNet [8] , Inception [9] , and Xception [10] .”
Das, P. K., & Meher, S. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115311 · Cited by 186
Fuhad, K. M. F., Tuba, J. F., Sarker, M. R. A., Momen, S., Mohammed, N., & Rahman, T. (2020) · Diagnostics · doi:10.3390/diagnostics10050329 · Cited by 185
“To find the optimal layer of a pre ‐ trained model to extract features from underlying malaria parasite data, Rajaraman et al. evaluated the performances of AlexNet, VGG ‐ 16 [50], ResNet ‐ 50 [51], Xception [52], DenseNet ‐ 121 [53] along with their custom ‐ built model [24].”
MethodReinforcement learning for neural architecture search: A review
Jaafra, Y., Luc Laurent, J., Deruyver, A., & Saber Naceur, M. (2019) · Image and Vision Computing · doi:10.1016/j.imavis.2019.06.005 · Cited by 183
Deep Learning Approaches on Pedestrian Detection in Hazy Weather
Li, G., Yang, Y., & Qu, X. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2945295 · Cited by 184
Cui, J., Lan, Z., Sourina, O., & Müller-Wittig, W. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3147208 · Cited by 181
Skin cancer detection using ensemble of machine learning and deep learning techniques
Tembhurne, J. V., Hebbar, N., Patil, H. Y., & Diwan, T. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14697-3 · Cited by 181
Hossain, S., & Lee, D.-J. (2019) · Sensors · doi:10.3390/s19153371 · Cited by 184
“It built on top of a powerful convolutional neural network (CNN) backbone architecture [57,58] to obtain the most accurate results, which are intended for server-side deployment.”
BackgroundISTVT: Interpretable Spatial-Temporal Video Transformer for Deepfake Detection
Zhao, C., Wang, C., Hu, G., Chen, H., Liu, C., & Tang, J. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3239223 · Cited by 184
Volumetric Correspondence Networks for Optical Flow
Yang, G., & Ramanan, D. (2019) · neural information processing systems · Cited by 275
TVQA+: Spatio-Temporal Grounding for Video Question Answering
Lei, J., Yu, L., Berg, T., & Bansal, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.730 · Cited by 113
Deep Learning for Optic Disc Segmentation and Glaucoma Diagnosis on Retinal Images
Sreng, S., Maneerat, N., Hamamoto, K., & Win, K. Y. (2020) · Applied Sciences · doi:10.3390/app10144916 · Cited by 184
Classification of COVID-19 chest X-rays with deep learning: new models or fine tuning?
Pham, T. D. (2021) · Health Information Science and Systems · doi:10.1007/s13755-020-00135-3 · Cited by 184
He, Q., Sun, X., Yan, Z., & Fu, K. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3045474 · Cited by 181
Recent Advancements in Fruit Detection and Classification Using Deep Learning Techniques
Ukwuoma, C. C., Zhiguang, Q., Bin Heyat, M. B., Ali, L., Almaspoor, Z., & Monday, H. N. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/9210947 · Cited by 182
Suha, S. A., & Islam, M. N. (2022) · Scientific Reports · doi:10.1038/s41598-022-21724-0 · Cited by 179
Pang, S., Pang, C., Zhao, L., Chen, Y., Su, Z., Zhou, Y., Huang, M., Yang, W., Lu, H., & Feng, Q. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3025087 · Cited by 183
“In contrast to DeepLabv3 + , the deep convNet removes the middle flow of the Xception [30] for simplifying the network, and generates the low-level image representation for obtaining the details of the spine.”
BackgroundSatellite Image Classification with Deep Learning
Pritt, M., & Chern, G. (2017) · 2017 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) · doi:10.1109/aipr.2017.8457969 · Cited by 182
Multi-scale Context Intertwining for Semantic Segmentation
Lin, D., Ji, Y., Lischinski, D., Cohen-Or, D., & Huang, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_37 · Cited by 173
“Fully convolutional networks (FCNs) [7] have proved effective for semantic image segmentation by leveraging the powerful convolutional features of classification networks [29, 30, 27] pre-trained on large-scale data [10, 24].”
BackgroundImplicit Identity Driven Deepfake Face Swapping Detection
Huang, B., Wang, Z., Yang, J., Ai, J., Zou, Q., Wang, Q., & Ye, D. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00436 · Cited by 172
Brain tumor detection from images and comparison with transfer learning methods and 3-layer CNN
Khaliki, M. Z., & Başarslan, M. S. (2024) · Scientific Reports · doi:10.1038/s41598-024-52823-9 · Cited by 181
“First introduced in a paper titled "Going Deeper with Convolutions", the Inception architecture aims to provide better performance when processing complex visual datasets 25 .”
BackgroundDeepfakes Detection with Automatic Face Weighting
Montserrat, D. M., Hao, H., Yarlagadda, S. K., Baireddy, S., Shao, R., Horvath, J., Bartusiak, E., Yang, J., Guera, D., Zhu, F., et al. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00342 · Cited by 181
“We also evaluate two CNNs: EfficientNet [42] and Xception [37].”
InfluentialMachine learning and deep learning algorithms for skin cancer classification from dermoscopic images
Bechelli, S., & Delhommelle, J. (2022) · Bioengineering · doi:10.3390/bioengineering9030097 · Cited by 181
“ML models include logistic regression, linear discriminant analysis, k-nearest neighbors classifier, decision tree classifier, and Gaussian naive Bayes, while DL models consist of a custom Convolutional Neural Network (CNN) model and pre-trained models, such as VGG16, Xception, and ResNet50.”
MethodInfluentialAugmented Ultrasonic Data for Machine Learning
Virkkunen, I., Koskinen, T., Jessen-Juhler, O., & Rinta-aho, J. (2021) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-020-00739-5 · Cited by 175
Toward Compact ConvNets via Structure-Sparsity Regularized Filter Pruning
Lin, S., Ji, R., Li, Y., Deng, C., & Li, X. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2906563 · Cited by 180
Boguszewski, A., Batorski, D., Ziemba-Jankowska, N., Dziedzic, T., & Zambrzycka, A. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00121 · Cited by 164
“We used Xception71 DPC pretrained on Cityscapes [12] to initialize weights and set decoder output stride = 4.”
MethodHasan, M. K., Elahi, M. T. E., Alam, M. A., Jawad, M. T., & Martí, R. (2022) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2021.100819 · Cited by 181
FocalClick: Towards Practical Interactive Image Segmentation
Chen, X., Zhao, Z., Zhang, Y., Duan, M., Qi, D., & Zhao, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00136 · Cited by 171
Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
Haliassos, A., Mira, R., Petridis, S., & Pantic, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01453 · Cited by 180
“However, an unconstrained Xception [23] network outperforms these approaches on more recent forgery types [89].”
BackgroundImproving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features
Sun, Z., Han, Y., Hua, Z., Ruan, N., & Jia, W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00361 · Cited by 180
Context-aware convolutional neural network for grading of colorectal cancer histology images
Shaban, M., Awan, R., Fraz, M. M., Azam, A., Tsang, Y.-W., Snead, D., & Rajpoot, N. M. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2971006 · Cited by 179
Tetila, E. C., Machado, B. B., Menezes, G. K., Da Silva Oliveira, A., Alvarez, M., Amorim, W. P., De Souza Belete, N. A., Da Silva, G. G., & Pistori, H. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2019.2932385 · Cited by 173
“We used an opensource implementation comprising CNNs, including Inceptionv3 [19], VGG-19 [20], ResNet-50 [21], and Xception [22], which are provided as part of the Keras module and it was recognized as validation on ImageNet.”
MethodAutomatic Detection of Diabetic Eye Disease Through Deep Learning Using Fundus Images: A Survey
Sarki, R., Ahmed, K., Wang, H., & Zhang, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3015258 · Cited by 176
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.