图像分类(Classification)
- LeNet http://yann.lecun.com/exdb/lenet/index.html
- AlexNet http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
- VGGNet https://arxiv.org/abs/1409.1556
- GoogLeNet, Inceptionv1(Going deeper with convolutions) https://arxiv.org/abs/1409.4842
- GoogLeNet, Inceptionv2(Batch Normalization)https://arxiv.org/abs/1502.03167
- GoogLeNet,Inceptionv3(Rethinking the Inception Architecture for Computer Vision) https://arxiv.org/abs/1512.00567
- GoogLeNet,Inceptionv4, Inception-ResNet https://arxiv.org/abs/1602.07261
- ResNet https://arxiv.org/abs/1512.03385
- ResNeXt https://arxiv.org/abs/1611.05431
- DenseNet https://arxiv.org/abs/1608.06993
- SENet(Squeeze-and-Excitation Networks) https://arxiv.org/abs/1709.01507
- MobileNet(v1) https://arxiv.org/abs/1704.04861
- MobileNet(v2) https://arxiv.org/abs/1801.04381
- MobileNet(v3) https://arxiv.org/abs/1905.02244
- ShuffleNet(v1) https://arxiv.org/abs/1707.01083
- ShuffleNet(v2) https://arxiv.org/abs/1807.11164
- EfficientNet(v1) https://arxiv.org/abs/1905.11946
- EfficientNet(v2) https://arxiv.org/abs/2104.00298
- CSPNet https://arxiv.org/abs/1911.11929
- Vision Transformer https://arxiv.org/abs/2010.11929
- Swin Transformer https://arxiv.org/abs/2103.14030
- ConvNeXt(A ConvNet for the 2020s)https://arxiv.org/abs/2201.03545
目标检测(Object Detection)
-
Fast R-CNN https://arxiv.org/abs/1504.08083
-
Faster R-CNN https://arxiv.org/abs/1506.01497
-
FPN(Feature Pyramid Networks for Object Detection) https://arxiv.org/abs/1612.03144
-
Focal Loss(Focal Loss for Dense Object Detection)https://arxiv.org/abs/1708.02002
-
DIOU(Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression)https://arxiv.org/abs/1911.08287
-
Group Normalization https://arxiv.org/abs/1803.08494
-
CutMix: Regularization Strategy to Train Strong Classifiers
with Localizable Features(YOLOv4) https://arxiv.org/abs/1905.04899 -
MMDetection: Open MMLab Detection Toolbox and Benchmark(目标检测开源工具箱)https://arxiv.org/abs/1906.07155
-
YOLOX: Exceeding YOLO Series in 2021 https://arxiv.org/abs/2107.08430
目标跟踪 -
Sort(Simple Online And Realtime Tracking) https://arxiv.org/abs/1602.00763
-
DeepSort(Simple Online and Realtime Tracking with a Deep Association Metric)https://arxiv.org/abs/1703.07402
图像分割(Segmentation)
- FCN(Fully Convolutional Networks for Semantic Segmentation) https://arxiv.org/abs/1411.4038
- UNet(U-Net: Convolutional Networks for Biomedical Image Segmentation) https://arxiv.org/abs/1505.04597
- PAN(Path Aggregation Network for Instance Segmentation) https://arxiv.org/pdf/1803.01534.pdf
- DeepLabv1(Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs) https://arxiv.org/abs/1412.7062
- DeepLabv2(Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs) https://arxiv.org/abs/1606.00915
- DeepLabv3(Rethinking Atrous Convolution for Semantic Image Segmentation) https://arxiv.org/abs/1706.05587
- DeepLabv3+(Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation) https://arxiv.org/abs/1802.02611
- Mask R-CNN https://arxiv.org/abs/1703.06870
3D点云
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation https://arxiv.org/abs/1612.00593
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space https://arxiv.org/abs/1706.02413
NLP
- Attention Is All You Need https://arxiv.org/abs/1706.03762
数据集
- Microsoft COCO: Common Objects in Context https://arxiv.org/abs/1405.0312
- The PASCALVisual Object Classes Challenge: A Retrospective http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham15.pdf