Deep Learning Paper

2023-06-014 分钟阅读2000 字

Paper

Image Classification

ALexNet：ImageNet Classification with Deep Convolutional Neural Networks (NIPS 2012)

ZFNet：Visualizing and Understanding Convolutional Networks (ECCV 2014)

GoogLeNet：Going Deeper with Convolutions (CVPR 2015)

Network In Network $1\times1$卷积
Provable Bounds for Learning Some Deep Representations 用稀疏、分散的网络取代以前庞大密集臃肿的网络
InceptionV2：Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (ICML 2015)
InceptionV3：Rethinking the Inception Architecture for Computer Vision (CVPR 2016)
InceptionV4：Inception-ResNet and the Impact of Residual Connections on Learning (AAAI 2017)
Xception：Xception: Deep Learning with Depthwise Separable Convolutions (CVPR 2017)

VGGNet：Very Deep Convolutional Networks for Large-Scale Visual Recognition (ICLR 2015)

ResNet：Deep Residual Learning for Image Recognition(CVPR 2016)

ResNeXt：ggregated Residual Transformations for Deep Neural Networks-2017
DenseNet：Densely Connected Convolutional Networks

Object Detection

Dense Prediction (one-stage)

anchor based

SSD：SSD: Single Shot MultiBox Detector (ECCV 2016)

YOLO：You Only Look Once:Unified, Real-Time Object Detection (CVPR 2016)

YOLOV2：YOLO9000: Better, Faster, Stronger (CVPR 2017)
YOLOV3：YOLOv3: An Incremental Improvement (CVPR 2018)
YOLOV4：YOLOv4: Optimal Speed and Accuracy of Object Detection (CVPR 2020)
Scaled-YOLOv4：Scaled-YOLOv4: Scaling Cross Stage Partial Network (CVPR 2021)
IOU_Loss(2016)->GIOU_Loss(2019)->DIOU_Loss(2020)->CIOU_Loss(2020)
YOLOX：YOLOX: Exceeding YOLO Series in 2021
YOLOV5：
Alpha-IoU:A Family of Power Intersection over Union Losses for Bounding Box Regression (NIPS 2021)

RetinaNet：Focal Loss for Dense Object Detection (ICCV 2017)

anchor free

CornerNet：CornerNet: Detecting Objects as Paired Keypoints](https://arxiv.org/abs/1808.01244) (ECCV 2018)

CornerNet-Lite: Efficient Keypoint Based Object Detection (BMVC 2020)

CenterNet：CenterNet: Keypoint Triplets for Object Detection (ICCV 2019)

MatrixNet：Matrix Nets: A New Deep Architecture for Object Detection (ICCV 2019)

FCOS：FCOS: Fully Convolutional One-Stage Object Detection (ICCV 2019)

Grounding DINO： Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection (2023)

Sparse Prediction (two-stage)

anchor based

R-CNN：[Rich feature hierarchies for accurate object detection and semantic segmentation (CVPR 2014)

Selective Search for Object Recognition (IJCV 2012)
[Path-aggregation blocks-FPN](####Path-aggregation blocks)
[Additional blocks-SPP](####Additional blocks)
Fast R-CNN：Fast R-CNN (ICCV 2015)
Faster R-CNN：Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (NIPS 2015)
R-FCN：R-FCN: Object Detection via Region-based Fully Convolutional Networks (NIPS 2016)
Mask R-CNN：Mask R-CNN (ICCV 2017)
Libra R-CNN: Libra R-CNN: Towards Balanced Learning for Object Detection (CVPR 2019)
Sparse R-CNN：Sparse R-CNN: End-to-End Object Detection with Learnable Proposals (CVPR 2021)

anchor free

RepPoints：RepPoints: Point Set Representation for Object Detection (ICCV 2019)

Neck

Additional blocks

SPP：Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (TPAMI 2015)
ASPP：DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (TPAMI 2017)
RFB：Receptive Field Block Net for Accurate and Fast Object Detection (ECCV 2018)
SAM：CBAM: Convolutional Block Attention Module (ECCV 2018)

Path-aggregation blocks

FPN：Feature Pyramid Networks for Object Detection (CVPR 2017)
PAN：Path Aggregation Network for Instance Segmentation (CVPR 2018)
NAS-FPN：NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (CVPR 2019)
BiFPN：EfficientDet: Scalable and Efficient Object Detection (CVPR 2020)
ASFF：Learning Spatial Fusion for Single-Shot Object Detection (2019)
SFAM： M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network (AAAI 2019)

轻量化CNN

SqueezeNet：SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size (2016)

SqueezeNext: Hardware-Aware Neural Network Design (2018)

MobileNet：MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (2017)

MobileNetV2：MobileNetV2: Inverted Residuals and Linear Bottlenecks (2018)
MobileNetV3：Searching for MobileNetV3 (2019)
MnasNet: Platform-Aware Neural Architecture Search for Mobile (CVPR 2019)

ShuffleNet：ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices (2017)