mlsanityData to 14 Oct 2026

Xception: Deep Learning with Depthwise Separable Convolutions

arXiv 1610.02357 ↗First posted 7 Oct 2016cs.CVcited by 2,332

Not on the map. Why?

Cited by 43 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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.

Key facts. Cited by 2,332 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 481; 2022: 450; 2023: 470; 2024: 404; 2025: 344; 2026: 183.

2,332 papers.

Sort:

By area:

  1. 2022A ConvNet for the 2020scited by 3,579
  2. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  3. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  4. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  5. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  6. 2024VMamba: Visual State Space Modelcited by 969
  7. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  8. 2022Language-driven Semantic Segmentationcited by 717
  9. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  10. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  11. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  12. 2022Vision Transformer Adapter for Dense Predictionscited by 565
38 more
  1. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  2. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  3. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  4. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
  5. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  7. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  8. 2023DIRE for Diffusion-Generated Image Detectioncited by 390
  9. 2021Multi-attentional Deepfake Detectioncited by 341
  10. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 339
  11. 2021AudioCLIP: Extending CLIP to Image, Text and Audiocited by 339
  12. 2022Detecting Deepfakes with Self-Blended Imagescited by 338
  13. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  14. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  15. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 262
  16. 2022Vision Transformers for Single Image Dehazingcited by 260
  17. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  18. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 249
  19. 2022Transformers in Medical Imaging: A Surveycited by 245
  20. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 244
  21. 2021TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditionscited by 244
  22. 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 209
  23. 2023Controlling Text-to-Image Diffusion by Orthogonal Finetuningcited by 208
  24. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  25. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 188
  26. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
  27. 2021RedCaps: web-curated image-text data created by the people, for the peoplecited by 180
  28. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 178
  29. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 173
  30. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  31. 2023EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attentioncited by 172
  32. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  33. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 166
  34. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 165
  35. 2023Neural Video Compression with Diverse Contextscited by 165
  36. 2022Compute Trends Across Three Eras of Machine Learningcited by 163
  37. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 159
  38. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155

50 most cited of 2,332 All 2,332 (JSON)