Awesome-Computer Vision Classification paper

1. ImageNet Classification with Deep Convolutional Neural Networks, 2012, NIPS, Spotlight, Paper, Official Code, Open Review, Review
2. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, 2014, ECCV, Paper
3. Visualizing and Understanding Convolutional Networks, 2014, ECCV, Paper
4. Network In Network, 2014, ICLR, Paper
5. OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, 2014, ICLR, Paper
6. Very Deep Convolutional Networks for Large-Scale Image Recognition, 2015, ICLR, Oral, Paper
7. Going Deeper with Convolutions, 2015, CVPR, Oral, Paper
8. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, 2015, ICCV, Paper
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, 2015, ICML, Paper
10. Spatial Transformer Networks, 2015, NIPS, Paper
11. Rethinking the Inception Architecture for Computer Vision, 2016, CVPR, Paper
12. Deep Residual Learning for Image Recognition, 2016, CVPR, Oral, Best Paper Award, Paper
13. Learning Deep Features for Discriminative Localization, 2016, CVPR, Paper
14. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size, 2016, Arxiv, Paper
15. Identity Mappings in Deep Residual Networks, 2016, ECCV, Spotlight, Paper
16. Wide Residual Networks, 2016, BMVC, Paper
17. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, 2017, AAAI, Paper
18. Densely Connected Convolutional Networks, 2017, CVPR, Oral, Best Paper Award, Paper
19. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization, 2017, ICCV, Paper
20. Deep Pyramidal Residual Networks, 2017, CVPR, Paper
21. Xception: Deep Learning with Depthwise Separable Convolutions, 2017, CVPR, Paper
22. Aggregated Residual Transformations for Deep Neural Networks, 2017, CVPR, Paper
23. PolyNet: A Pursuit of Structural Diversity in Very Deep Networks, 2017, CVPR, Paper
24. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, 2017, CoRR, Paper
25. Dynamic Routing Between Capsules, 2017, NIPS, Paper
26. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices, 2018, CVPR, Paper
27. Squeeze-and-Excitation Networks, 2018, CVPR, Oral, Paper
28. Non-local Neural Networks, 2018, CVPR, Paper
29. MobileNetV2: Inverted Residuals and Linear Bottlenecks, 2018, CVPR, Paper
30. Exploring the Limits of Weakly Supervised Pretraining, 2018, ECCV, Paper
31. How Does Batch Normalization Help Optimization?, 2018, NIPS, Oral, Paper
32. Understanding Batch Normalization, 2018, NIPS, Paper
33. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design, 2019, ECCV, Paper
34. Bag of Tricks for Image Classification with Convolutional Neural Networks, 2019, CVPR, Paper
35. Searching for MobileNetV3, 2019, ICCV, Oral, Paper
36. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, 2019, ICML, Oral, Paper
37. When Does Label Smoothing Help?, 2019, NIPS, Spotlight, Paper
38. Stand-Alone Self-Attention in Vision Models, 2019, NIPS, Paper
39. Fixing the train-test resolution discrepancy, 2019, NIPS, Paper
40. Self-training with Noisy Student improves ImageNet classification, 2020, CVPR, Paper
41. Adversarial Examples Improve Image Recognition, 2020, CVPR, Paper
42. Big Transfer (BiT): General Visual Representation Learning, 2020, ECCV, Spotlight, Paper
43. Fixing the train-test resolution discrepancy: FixEfficientNet, 2020, Arxiv, Paper
44. Sharpness-Aware Minimization for Efficiently Improving Generalization, 2021, ICLR, Spotlight, Paper
45. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, 2021, ICLR, Oral, Paper
46. Training data-efficient image transformers & distillation through attention, Paper
47. High-Performance Large-Scale Image Recognition Without Normalization, Paper