Levers are simple too, but they can move the world1.文章目录1、Categories【Classification】【Data Augmentation】【Object Detection】【Segmentation】【Face Classification / Detection / Recognition】【Point Detection】【Tracking】【ReID】【Depth】【High Resolution / Super Resolution】【One Shot】【Noisy Label】【3D】【AIGC】2、期刊会议2.1、期刊2.2、会议沈向洋：读论文的三个层次disconnect between author’s intent and reader’s learning例如，直到现在人们还在争论孔子写过的那些文字到底是什么意思它更多是一个反复的理解过程，阅读等同于理解，不同层次的阅读对应不同层次的理解1、Categories【Classification】【NIN】《Network In Network》（arXiv-2013）【Mixed Pooling】《Mixed Pooling for Convolutional Neural Networks》（RSKT-2014）【Distilling】《Distilling the Knowledge in a Neural Network》（arXiv-2015, In NIPS Deep Learning Workshop, 2014）【Highway network】《Training Very Deep Networks》（NIPS-2015）【Inception-v1】《Going Deeper with Convolutions》（CVPR-2015）【Inception-v2】《Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift》（ICML-2015）【Inception-v3】《Rethinking the Inception Architecture for Computer Vision》（CVPR-2016）【WRNs】《Wide Residual Networks》（arXiv-2016）【Stochastic Depth】《Deep Networks with Stochastic Depth》（ECCV-2016）【Comprssion】《Deep Compression：Compressing Deep Neural Networks with Pruning，Trained Quantization and Huffman Coding》（ICLR-2016 Best Paper）【SGDR】《SGDR：Stochastic Gradient Descent with Warm Restarts》（arXiv-2016）【CLR】《Cyclical Learning Rates for Training Neural Networks》（WACV-2017）【Distilling】《Learning Efficient Object Detection Models with Knowledge Distillation》（NIPS-2017）【RSCM】《RSCM：Region selection and concurrency model for multi-class weather recognition》（TIP-2017）【Inception-v4、Inception-Resnet-v1、v2】《Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning》（AAAI-2017）【SqueezeNet】《SqueezeNet：AlexNet-Level accuracy with 50× fewer parameters and 0.5MB model size》（ICLR-2017）【Snapshot Ensembles】《Snapshot Ensembles：Train 1，Get M for Free》（ICLR-2017）【DenseNet】《Densely Connected Convolutional Networks》（CVPR-2017）【Xception】《Xception: Deep Learning with Depthwise Separable Convolutions》（CVPR-2017）【ResNext】《Aggregated Residual Transformations for Deep Neural Networks》（CVPR-2017）【MobileNet】《MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications》（CVPR-2017）【NasNet】《Learning Transferable Architectures for Scalable Image Recognition》（CVPR-2018）【SENet】《Squeeze-and-Excitation Networks》（CVPR-2018）【ShuffleNet】《ShuffleNet：An Extremely Efficient Convolutional Neural Network for Mobile Devices》（CVPR-2018）【MobileNet V2】《MobileNetV2：Inverted Residuals and Linear Bottlenecks》（CVPR-2018）【ShuffleNet V2】《ShuffleNet V2：Practical Guidelines for Efficient CNN Architecture Design》（ECCV-2018）【CBAM】《CBAM: Convolutional Block Attention Module》（ECCV-2018）【Bilinear Pooling】《A Novel DR Classfication Scheme based on Compact Bilinear Pooling CNN and GBDT》（JIH-MSP-2018）【FD-MobileNet】《FD-MobileNet：Improved MobileNet with a Fast Downsampling Strategy》（ICIP-2018）【SKNet】《Selective Kernel Networks》（CVPR-2019）【BoT】《Bag of Tricks for Image Classification with Convolutional Neural Networks》（CVPR-2019）【C3AE】《C3AE：Exploring the Limits of Compact Model for Age Estimation》（CVPR-2019）【MnasNet】《MnasNet：Platform-Aware Neural Architecture Search for Mobile》（CVPR-2019）【EfficientNet】《EfficientNet：Rethinking Model Scaling for Convolutional Neural Networks》（ICML-2019）【MobileNet V3】《Searching for MobileNetV3》（ICCV-2019）【RegNet】《Designing Network Design Spaces》（CVPR-2020）【GhostNet】《GhostNet：More Features from Cheap Operations》（CVPR-2020）【CSPNet】《CSPNet：A New Backbone that can Enhance Learning Capability of CNN》（CVPRW-2020）【RepVGG】《RepVGG：Making VGG-style ConvNets Great Again》（CVPR-2021）【DBBConv】《Diverse Branch Block: Building a Convolution as an Inception-like Unit》（CVPR-2021）【CA】《Coordinate Attention for Efficient Mobile Network Design》（CVPR-2021）【Shuffle Attention】《SA-Net：Shuffle Attention for Deep Convolutional Neural Networks》（ICASSP-2021）【NAM】《NAM：Normalization-based Attention Module》（NeurIPS-2021 workshop）【GAM】《Global Attention Mechanism：Retain Information to Enhance Channel-Spatial Interactions》（arXiv-2021）【EfficientNetV2】《EfficientNetV2: Smaller Models and Faster Training》（ICML-2021）【SPD-Conv】《No More Strided Convolutions or Pooling：A New CNN Building Block for Low-Resolution Images and Small Objects》（ECML-PKDD-2022）【Transformer】Introduction to Transformer（learning notes）【Transformer】Transformer and BERT（1）（learning notes）【Transformer】ViT and TNT（2）（learning notes）【MobileNetV4】《MobileNetV4：Universal Models for the Mobile Ecosystem》（ECCV-2024）【E-ConvNeXt】《E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections》（arXiv-2025）【CPUBone】CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities（CPVR-2026-finding）【Data Augmentation】AgaMiko/data-augmentation-review【Cutout】《Improved Regularization of Convolutional Neural Networks with Cutout》（arXiv-2017）【Hide-and-Seek】《Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond》（ICCV-2017）
