本資源整理了深度學習/圖像處理技術發展過程中的所有模型、優化技巧、網絡結構優化、迭代過程中所有經典論文，並進行了詳細的分類，按重要程度進行了仔細的劃分，對於想要了解深度學習模型迭代朋友來說非常值得參考。
本資源整理自網絡，源地址：https://github.com/xw-hu/Reading-List
基礎模型和技巧
•AlexNet: MLA Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012. ⭐️⭐️⭐️⭐️⭐️
•Dropout: Srivastava, Nitish, et al. "Dropout: a simple way to prevent neural networks from overfitting." Journal of Machine Learning Research 15.1 (2014): 1929-1958. ⭐️⭐️⭐️⭐️
•VGG: Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014). ⭐️⭐️⭐️⭐️⭐️
•GoogLeNet: Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. ⭐️⭐️⭐️⭐️⭐️
•Batch Normalization: Ioffe, Sergey, and Christian Szegedy. "Batch normalization: Accelerating deep network training by reducing internal covariate shift." arXiv preprint arXiv:1502.03167 (2015). [Inception v2] ⭐️⭐️⭐️⭐️⭐️
•PReLU & msra Initilization: He, Kaiming, et al. "Delving deep into rectifiers: Surpassing human-level performance on imagenet classification." Proceedings of the IEEE international conference on computer vision. 2015. ⭐️⭐️⭐️⭐️⭐️
•InceptionV3: Szegedy, Christian, et al. "Rethinking the inception architecture for computer vision." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️
•ResNet: He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️⭐️
•Identity ResNet: He, Kaiming, et al. "Identity mappings in deep residual networks." European Conference on Computer Vision. Springer International Publishing, 2016. ⭐️⭐️⭐️⭐️⭐️
•CReLU: Shang, Wenling, et al. "Understanding and improving convolutional neural networks via concatenated rectified linear units." Proceedings of the International Conference on Machine Learning (ICML). 2016. ⭐️⭐️⭐️
•InceptionV4 & Inception-ResNet: Szegedy, Christian, et al. "Inception-v4, inception-resnet and the impact of residual connections on learning." arXiv preprint arXiv:1602.07261 (2016). ⭐️⭐️⭐️⭐️
•ResNeXt: Xie, Saining, et al. "Aggregated residual transformations for deep neural networks." arXiv preprint arXiv:1611.05431 (2016). ⭐️⭐️⭐️⭐️
•Batch Renormalization: Ioffe, Sergey. "Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models." arXiv preprint arXiv:1702.03275 (2017). ⭐️⭐️⭐️⭐️
•Xception: Chollet, François. "Xception: Deep Learning with Depthwise Separable Convolutions." arXiv preprint arXiv:1610.02357 (2016). ⭐️⭐️⭐️
•MobileNets: Howard, Andrew G., et al. "Mobilenets: Efficient convolutional neural networks for mobile vision applications." arXiv preprint arXiv:1704.04861 (2017). ⭐️⭐️⭐️
•DenseNet: Huang, Gao, et al. "Densely connected convolutional networks." arXiv preprint arXiv:1608.06993 (2016). ⭐️⭐️⭐️⭐️⭐️
•PolyNet: Zhang, Xingcheng, et al. "Polynet: A pursuit of structural diversity in very deep networks." arXiv preprint arXiv:1611.05725 (2016). Slides ⭐️⭐️⭐️⭐️
•IRNN: Le, Quoc V., Navdeep Jaitly, and Geoffrey E. Hinton. "A simple way to initialize recurrent networks of rectified linear units." arXiv preprint arXiv:1504.00941 (2015). ⭐️⭐️⭐️
•ReNet: Visin, Francesco, et al. "ReNet: A recurrent neural network based alternative to convolutional networks." arXiv preprint arXiv:1505.00393 (2015). ⭐️⭐️⭐️⭐️
•Non-local Neural Network: Wang, Xiaolong, Ross Girshick, Abhinav Gupta, and Kaiming He. "Non-local Neural Networks." arXiv preprint arXiv:1711.07971 (2017). ⭐️⭐️⭐️⭐️
•Group Normalization: Wu, Yuxin, and Kaiming He. "Group normalization." In ECCV (2018). ⭐️⭐️⭐️⭐️⭐️
•SENet: Hu, Jie, Li Shen, and Gang Sun. "Squeeze-and-excitation networks."In CVPR (2018). ⭐️⭐️⭐️⭐️⭐️
•Rethinking ImageNet Pre-training：He, Kaiming, Ross Girshick, and Piotr Dollár. "Rethinking ImageNet Pre-training." arXiv preprint arXiv:1811.08883 (2018). ⭐️⭐️⭐️⭐️
•CBAM：Woo, Sanghyun, et al. "CBAM: Convolutional block attention module." Proceedings of the European Conference on Computer Vision (ECCV). 2018. ⭐️⭐️⭐️⭐️
•Network generator: Saining Xie, Alexander Kirillov, Ross Girshick, Kaiming He. Exploring Randomly Wired Neural Networks for Image Recognition. arXiv:1904.01569 (2019). ⭐️⭐️⭐️⭐️⭐️
•GCNet: Cao, Yue, et al. "GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond." arXiv preprint arXiv:1904.11492 (2019). ⭐️⭐️⭐️⭐️
物體檢測
•Overfeat: Sermanet, Pierre, et al. "Overfeat: Integrated recognition, localization and detection using convolutional networks." arXiv preprint arXiv:1312.6229 (2013). ⭐️⭐️⭐️⭐️
•RCNN: Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. ⭐️⭐️⭐️⭐️⭐️
•SPP: He, Kaiming, et al. "Spatial pyramid pooling in deep convolutional networks for visual recognition." European Conference on Computer Vision. Springer International Publishing, 2014. ⭐️⭐️⭐️⭐️⭐️
•Fast RCNN: Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE International Conference on Computer Vision. 2015. ⭐️⭐️⭐️⭐️⭐️
•Faster RCNN: Ren, Shaoqing, et al. "Faster r-cnn: Towards real-time object detection with region proposal networks." Advances in neural information processing systems. 2015. ⭐️⭐️⭐️⭐️⭐️
•R-CNN minus R: Lenc, Karel, and Andrea Vedaldi. "R-cnn minus r." arXiv preprint arXiv:1506.06981 (2015). ⭐️
•End-to-end people detection in crowded scenes: Stewart, Russell, Mykhaylo Andriluka, and Andrew Y. Ng. "End-to-end people detection in crowded scenes." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️
•YOLO: Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️⭐️
•ION: Bell, Sean, et al. "Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️
•MultiPath: Zagoruyko, Sergey, et al. "A multipath network for object detection." arXiv preprint arXiv:1604.02135 (2016). ⭐️⭐️⭐️
•SSD: Liu, Wei, et al. "SSD: Single shot multibox detector." European Conference on Computer Vision. Springer International Publishing, 2016. ⭐️⭐️⭐️⭐️⭐️
•OHEM: Shrivastava, Abhinav, Abhinav Gupta, and Ross Girshick. "Training region-based object detectors with online hard example mining." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️⭐️
•HyperNet: Kong, Tao, et al. "HyperNet: towards accurate region proposal generation and joint object detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️
•SDP: Yang, Fan, Wongun Choi, and Yuanqing Lin. "Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️
•SubCNN: Xiang, Yu, et al. "Subcategory-aware convolutional neural networks for object proposals and detection." Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on. IEEE, 2017. ⭐️⭐️⭐️
•MSCNN: Cai, Zhaowei, et al. "A unified multi-scale deep convolutional neural network for fast object detection." European Conference on Computer Vision. Springer International Publishing, 2016. ⭐️⭐️⭐️⭐️
•RFCN: Li, Yi, Kaiming He, and Jian Sun. "R-fcn: Object detection via region-based fully convolutional networks." Advances in Neural Information Processing Systems. 2016. ⭐️⭐️⭐️⭐️⭐️
•Shallow Network: Ashraf, Khalid, et al. "Shallow networks for high-accuracy road object-detection." arXiv preprint arXiv:1606.01561 (2016). ⭐️⭐️
•Is Faster R-CNN Doing Well for Pedestrian Detection: Zhang, Liliang, et al. "Is Faster R-CNN Doing Well for Pedestrian Detection?." European Conference on Computer Vision. Springer International Publishing, 2016. ⭐️⭐️
•GCNN: Najibi, Mahyar, Mohammad Rastegari, and Larry S. Davis. "G-cnn: an iterative grid based object detector." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️
•LocNet: Gidaris, Spyros, and Nikos Komodakis. "Locnet: Improving localization accuracy for object detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️
•PVANet: Kim, Kye-Hyeon, et al. "PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection." arXiv preprint arXiv:1608.08021 (2016). ⭐️⭐️⭐️⭐️
•FPN: Lin, Tsung-Yi, et al. "Feature Pyramid Networks for Object Detection." arXiv preprint arXiv:1612.03144 (2016). ⭐️⭐️⭐️⭐️⭐️
•TDM: Shrivastava, Abhinav, et al. "Beyond Skip Connections: Top-Down Modulation for Object Detection." arXiv preprint arXiv:1612.06851 (2016). ⭐️⭐️⭐️⭐️
•YOLO9000: Redmon, Joseph, and Ali Farhadi. "YOLO9000: Better, Faster, Stronger." arXiv preprint arXiv:1612.08242 (2016). ⭐️⭐️⭐️⭐️
•Speed/accuracy trade-offs for modern convolutional object detectors: Huang, Jonathan, et al. "Speed/accuracy trade-offs for modern convolutional object detectors." arXiv preprint arXiv:1611.10012 (2016). ⭐️⭐️
•GDB-Net: Zeng, Xingyu, et al. "Crafting GBD-Net for Object Detection." arXiv preprint arXiv:1610.02579 (2016). Slides⭐️⭐️⭐️⭐️
•WRInception: Lee, Youngwan, et al. "Wide-Residual-Inception Networks for Real-time Object Detection." arXiv preprint arXiv:1702.01243 (2017). ⭐️
•DSSD: Fu, Cheng-Yang, et al. "DSSD: Deconvolutional Single Shot Detector." arXiv preprint arXiv:1701.06659 (2017). ⭐️⭐️⭐️⭐️
•A-Fast-RCNN (Hard positive generation): Wang, Xiaolong, Abhinav Shrivastava, and Abhinav Gupta. "A-fast-rcnn: Hard positive generation via adversary for object detection." arXiv preprint arXiv:1704.03414 (2017). ⭐️⭐️⭐️ code
•RRC: Ren, Jimmy, et al. "Accurate Single Stage Detector Using Recurrent Rolling Convolution." arXiv preprint arXiv:1704.05776 (2017). ⭐️⭐️⭐️
•Deformable ConvNets: Dai, Jifeng, et al. "Deformable Convolutional Networks." arXiv preprint arXiv:1703.06211 (2017). ⭐️⭐️⭐️⭐️
•RSSD: Jeong, Jisoo, Hyojin Park, and Nojun Kwak. "Enhancement of SSD by concatenating feature maps for object detection." arXiv preprint arXiv:1705.09587 (2017). ⭐️⭐️
•Perceptual GAN: Li, Jianan, et al. "Perceptual Generative Adversarial Networks for Small Object Detection." arXiv preprint arXiv:1706.05274 (2017). ⭐️⭐️⭐️
•RetinaNet (Focal Loss): Tsung-Yi Lin, Priya Goyal, Ross B. Girshick, Kaiming He, and Piotr Dollár. "Focal Loss for Dense Object Detection." In ICCV. 2017. ⭐️⭐️⭐️⭐️⭐️
•YOLOv3: Redmon, Joseph, and Ali Farhadi. "YOLOv3: An Incremental Improvement." arXiv preprint arXiv:1804.02767 (2018). ⭐️⭐️⭐️
•Domain Adaptive Faster R-CNN: Chen, Yuhua, et al. "Domain adaptive faster r-cnn for object detection in the wild." In CVPR, 2018. ⭐️⭐️⭐️⭐️
•OMNIA Faster R-CNN：Rame, Alexandre, et al. "OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation." arXiv preprint arXiv:1812.02611 (2018). [Omni-Supervised across different datasets for object detection] ⭐️⭐️⭐️⭐️
•Libra R-CNN: Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., & Lin, D. (2019). Libra R-CNN: Towards Balanced Learning for Object Detection. arXiv preprint arXiv:1904.02701. ⭐️⭐️⭐️⭐️
圖像切分
•FCN: Long, Jonathan, Evan Shelhamer, and Trevor Darrell. "Fully convolutional networks for semantic segmentation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. ⭐️⭐️⭐️⭐️⭐️
•Deconvolution Network for Segmentation: Noh, Hyeonwoo, Seunghoon Hong, and Bohyung Han. "Learning deconvolution network for semantic segmentation." Proceedings of the IEEE International Conference on Computer Vision. 2015. ⭐️⭐️⭐️
•U-Net: Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional networks for biomedical image segmentation." International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015. ⭐️⭐️⭐️⭐️⭐️
•CRF as RNN: Zheng, Shuai, et al. "Conditional random fields as recurrent neural networks." In ICCV. 2015. ⭐️⭐️⭐️⭐️
•MNC: Dai, Jifeng, Kaiming He, and Jian Sun. "Instance-aware semantic segmentation via multi-task network cascades." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️⭐️
•InstanceFCN: Dai, Jifeng, et al. "Instance-sensitive fully convolutional networks." arXiv preprint arXiv:1603.08678 (2016). ⭐️⭐️⭐️⭐️
•FCIS: Li, Yi, et al. "Fully convolutional instance-aware semantic segmentation." arXiv preprint arXiv:1611.07709 (2016). ⭐️⭐️⭐️⭐️⭐️
•PSPNet: Zhao, Hengshuang, et al. "Pyramid scene parsing network." arXiv preprint arXiv:1612.01105 (2016). ⭐️⭐️⭐️
•Deeplab v1v2: Chen, Liang-Chieh, et al. "Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs." IEEE transactions on pattern analysis and machine intelligence 40.4 (2018): 834-848. ⭐️⭐️⭐️⭐️⭐️
•Deeplab v3: Chen, Liang-Chieh, et al. "Rethinking atrous convolution for semantic image segmentation." arXiv preprint arXiv:1706.05587 (2017). ⭐️⭐️⭐️
•Deeplab v3+: Chen, Liang-Chieh, et al. "Encoder-decoder with atrous separable convolution for semantic image segmentation." arXiv preprint arXiv:1802.02611 (2018). ⭐️⭐️⭐️
•Mask R-CNN: He, Kaiming, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. "Mask r-cnn." In ICCV. 2017. ⭐️⭐️⭐️⭐️⭐️
•Learning to Segment Every Thing (Mask^X R-CNN): Hu, Ronghang, Piotr Dollár, Kaiming He, Trevor Darrell, and Ross Girshick. "Learning to Segment Every Thing." arXiv preprint arXiv:1711.10370 (2017). ⭐️⭐️⭐️⭐️⭐️
•PANet: Liu, Shu, et al. "Path aggregation network for instance segmentation." arXiv preprint arXiv:1803.01534 (2018). ⭐️⭐️⭐️⭐️
•Panoptic Segmentation: Kirillov, A., He, K., Girshick, R., Rother, C., & Dollár, P. (2018). Panoptic Segmentation. arXiv preprint arXiv:1801.00868. ⭐️⭐️⭐️⭐️
•PSANet: Zhao, Hengshuang, et al. "PSANet: Point-wise Spatial Attention Network for Scene Parsing." Proceedings of the European Conference on Computer Vision (ECCV). 2018. ⭐️⭐️⭐️⭐️ [good summary of context information]
•OCNet: Yuan, Yuhui, and Jingdong Wang. "OCNet: Object Context Network for Scene Parsing." arXiv preprint arXiv:1809.00916 (2018). ⭐️⭐️⭐️
•ReSeg: Visin, Francesco, et al. "Reseg: A recurrent neural network-based model for semantic segmentation." In CVPR Workshops. 2016. ⭐️⭐️
•CCNet: Huang, Zilong, et al. "CCNet: Criss-Cross Attention for Semantic Segmentation." arXiv preprint arXiv:1811.11721 (2018). ⭐️⭐️⭐️
•Panoptic FPN: Kirillov, A., Girshick, R., He, K., & Dollár, P. (2019). Panoptic Feature Pyramid Networks. arXiv preprint arXiv:1901.02446. ⭐️⭐️⭐️⭐️⭐️
•Depth-aware CNN: Wang, Weiyue, and Ulrich Neumann. "Depth-aware CNN for RGB-D Segmentation." In ECCV, 2018. ⭐️⭐️⭐️⭐️⭐️
•Mask Scoring R-CNN: Huang, Z., Huang, L., Gong, Y., Huang, C., & Wang, X. (2019). Mask Scoring R-CNN. arXiv preprint arXiv:1903.00241. ⭐️⭐️⭐️⭐️
•DFANet: Li, H., Xiong, P., Fan, H., & Sun, J. (2019). DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation. arXiv preprint arXiv:1904.02216. ⭐️⭐️
•TensorMask：Chen, X., Girshick, R., He, K., & Dollár, P. (2019). TensorMask: A Foundation for Dense Object Segmentation. arXiv preprint arXiv:1903.12174. ⭐️⭐️⭐️⭐️
•DADA: Vu, Tuan-Hung, et al. "DADA: Depth-aware Domain Adaptation in Semantic Segmentation." arXiv preprint arXiv:1904.01886 (2019). ⭐️⭐️⭐️⭐️
•CFNet：Zhang, Hang, et al. "Co-Occurrent Features in Semantic Segmentation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️
•SSAP: Gao, Naiyu, et al. "SSAP: Single-shot instance segmentation with affinity pyramid." Proceedings of the IEEE International Conference on Computer Vision. 2019. ⭐️⭐️⭐️
•FCOS: Tian, Zhi, et al. "FCOS: Fully Convolutional One-Stage Object Detection." arXiv preprint arXiv:1904.01355 (2019). ⭐️⭐️⭐️⭐️⭐️
•EmbedMask: Ying, H., Huang, Z., Liu, S., Shao, T., & Zhou, K. (2019). EmbedMask: Embedding Coupling for One-stage Instance Segmentation. arXiv preprint arXiv:1912.01954. ⭐️⭐️⭐️⭐️⭐️
弱監督學習
•Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning: Cinbis, Ramazan Gokberk, Jakob Verbeek, and Cordelia Schmid. "Weakly supervised object localization with multi-fold multiple instance learning." IEEE transactions on pattern analysis and machine intelligence 39.1 (2017): 189-203. ⭐️⭐️⭐️
•Weakly Supervised Deep Detection Networks: Bilen, Hakan, and Andrea Vedaldi. "Weakly supervised deep detection networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️
•Weakly- and Semi-Supervised Learning: Papandreou, George, et al. "Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation." Proceedings of the IEEE International Conference on Computer Vision. 2015. ⭐️⭐️⭐️⭐️
•Image-level to pixel-level labeling: Pinheiro, Pedro O., and Ronan Collobert. "From image-level to pixel-level labeling with convolutional networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015.
•Weakly Supervised Localization using Deep Feature Maps: Bency, Archith J., et al. "Weakly supervised localization using deep feature maps." arXiv preprint arXiv:1603.00489 (2016).
•WELDON: Durand, Thibaut, Nicolas Thome, and Matthieu Cord. "Weldon: Weakly supervised learning of deep convolutional neural networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016.
•WILDCAT: Durand, Thibaut, et al. "WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation." The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017.
•SGDL: Lai, Baisheng, and Xiaojin Gong. "Saliency guided dictionary learning for weakly-supervised image parsing." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016.
無監督學習
•Learning Features by Watching Objects Move: Pathak, Deepak, et al. "Learning Features by Watching Objects Move." arXiv preprint arXiv:1612.06370 (2016). ⭐️⭐️⭐️⭐️⭐️
•SimGAN: Shrivastava, Ashish, et al. "Learning from simulated and unsupervised images through adversarial training." arXiv preprint arXiv:1612.07828 (2016). ⭐️⭐️⭐️
•OPN: Lee, Hsin-Ying, et al. "Unsupervised Representation Learning by Sorting Sequences." arXiv preprint arXiv:1708.01246 (2017). ⭐️⭐️⭐️
•Transitive Invariance for Self-supervised Visual Representation Learning: Wang, Xiaolong, et al. "Transitive Invariance for Self-supervised Visual Representation Learning" Proceedings of the IEEE International Conference on Computer Vision. 2017. ⭐️⭐️⭐️ code
•Omni-Supervised Learning: Radosavovic, I., Dollár, P., Girshick, R., Gkioxari, G., & He, K. Data Distillation: Towards Omni-Supervised Learning. In CVPR, 2018. ⭐️⭐️⭐️⭐️⭐️
顯著性檢測
•DHSNet: Liu, Nian, and Junwei Han. "Dhsnet: Deep hierarchical saliency network for salient object detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️
•RFCN: Wang, Linzhao, et al. "Saliency detection with recurrent fully convolutional networks." European Conference on Computer Vision. Springer International Publishing, 2016. ⭐️⭐️⭐️⭐️
•RACDNN: Kuen, Jason, Zhenhua Wang, and Gang Wang. "Recurrent attentional networks for saliency detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️⭐️
•NLDF: Luo, Zhiming, et al. "Non-Local Deep Features for Salient Object Detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. ⭐️⭐️⭐️
•DSS: Hou, Qibin, et al. "Deeply supervised salient object detection with short connections." arXiv preprint arXiv:1611.04849 (2016). ⭐️⭐️⭐️⭐️
•MSRNet: Li, Guanbin, et al. "Instance-Level Salient Object Segmentation." arXiv preprint arXiv:1704.03604 (2017). ⭐️⭐️⭐️⭐️
•Amulet: Zhang, Pingping, et al. "Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection." arXiv preprint arXiv:1708.02001 (2017). ⭐️⭐️⭐️⭐️
•UCF: Zhang, Pingping, et al. "Learning Uncertain Convolutional Features for Accurate Saliency Detection." arXiv preprint arXiv:1708.02031 (2017). ⭐️⭐️⭐️⭐️
•SRM: Wang, Tiantian, et al. "A Stagewise Refinement Model for Detecting Salient Objects in Images." In ICCV. 2017. ⭐️⭐️⭐️⭐️
•S4Net: Fan, Ruochen, et al. "$ S^ 4$ Net: Single Stage Salient-Instance Segmentation." arXiv preprint arXiv:1711.07618 (2017). ⭐️⭐️⭐️⭐️⭐️
•Deep Edge-Aware Saliency Detection：Zhang, Jing, Yuchao Dai, Fatih Porikli, and Mingyi He. "Deep Edge-Aware Saliency Detection." arXiv preprint arXiv:1708.04366 (2017). ⭐️⭐️⭐️
•Bi-Directional Message Passing Model: Zhang, Lu, et al. "A Bi-Directional Message Passing Model for Salient Object Detection." In CVPR. 2018. ⭐️⭐️⭐️
•PiCANet: Liu, Nian, Junwei Han, and Ming-Hsuan Yang. "PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection." In CVPR. 2018. ⭐️⭐️⭐️⭐️⭐️
•Detect Globally, Refine Locally: A Novel Approach to Saliency Detection: Wang, Tiantian, et al. "Detect Globally, Refine Locally: A Novel Approach to Saliency Detection." In CVPR. 2018. ⭐️⭐️⭐️
•PAGRN：Zhang, Xiaoning, et al. "Progressive Attention Guided Recurrent Network for Salient Object Detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. ⭐️⭐️⭐️
•Reverse Attention for Salient Object Detection: Chen, Shuhan, et al. "Reverse Attention for Salient Object Detection." In ECCV, 2018. ⭐️⭐️
•CA-Fuse: Chen, Hao, and Youfu Li. "Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection." In CVPR. 2018. ⭐️⭐️⭐️
•SOC dataset: Fan, Deng-Ping, et al. "Salient objects in clutter: Bringing salient object detection to the foreground." In ECCV. 2018. ⭐️⭐️⭐️⭐️⭐️ [complex dataset + instance level]
•DNA: Liu, Yun, et al. "DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection." arXiv preprint arXiv:1903.12476 (2019). ⭐️⭐️⭐️
•SE2Net：Zhou, S., Wang, J., Wang, F., & Huang, D. SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection. ⭐️⭐️⭐️⭐️⭐️
•PFAN: Zhao, T., & Wu, X. (2019). Pyramid Feature Selective Network for Saliency detection. In CVPR 2019. ⭐️⭐️
•PoolNet: Liu, Jiang-Jiang, et al. "A Simple Pooling-Based Design for Real-Time Salient Object Detection." In CVPR 2019. ⭐️⭐️⭐️⭐️
注意力機制
•SRN: Zhu, Feng, et al. "Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification." arXiv preprint arXiv:1702.05891 (2017). ⭐️⭐️⭐️⭐️
•Zoom-in-Net: Wang, Zhe, et al. "Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection." arXiv preprint arXiv:1706.04372 (2017). ⭐️⭐️⭐️⭐️
•Multi-context attention: Chu, Xiao, et al. "Multi-context attention for human pose estimation." arXiv preprint arXiv:1702.07432 (2017). ⭐️⭐️⭐️
深度信息和立體視覺
•HFM-Net: Zeng, J., Tong, Y., Huang, Y., Yan, Q., Sun, W., Chen, J., & Wang, Y. (2019). Deep Surface Normal Estimation with Hierarchical RGB-D Fusion. arXiv preprint arXiv:1904.03405. ⭐️⭐️⭐️
•MADNet: Tonioni, Alessio, et al. "Real-time self-adaptive deep stereo." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️⭐️ (offline domain adaption)
•Geometry-Aware Distillation: Jiao, Jianbo, et al. "Geometry-Aware Distillation for Indoor Semantic Segmentation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️
陰影檢測與消除
•DeshadowNet: Qu, Liangqiong, et al. "DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. ⭐️⭐️⭐️
•scGAN: Nguyen, Vu, et al. "Shadow Detection with Conditional Generative Adversarial Networks." In ICCV. 2017. ⭐️⭐️
•Patched CNN: Hosseinzadeh, Sepideh, Moein Shakeri, and Hong Zhang. "Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network." arXiv preprint arXiv:1709.09283 (2017). ⭐️
•ST-CGAN: Wang, Jifeng, et al. "Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal." arXiv preprint arXiv:1712.02478 (2017). ⭐️⭐️ (ISTD dataset)
•A+D Net: Le, Hieu, et al. "A+ D net: Training a shadow detector with adversarial shadow attenuation." Proceedings of the European Conference on Computer Vision (ECCV). 2018. ⭐️⭐️⭐️
•Lazy annotation for immature SBU：Vicente, Yago, et al. "Noisy label recovery for shadow detection in unfamiliar domains." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. ⭐️⭐️⭐️
•StackedCNN + SBU: Vicente, Tomás F. Yago, et al. "Large-scale training of shadow detectors with noisily-annotated shadow examples." European Conference on Computer Vision. Springer, Cham, 2016. ⭐️⭐️⭐️⭐️ (SBU dataset)
•CPAdv-Net: Mohajerani, Sorour, and Parvaneh Saeedi. "Shadow Detection in Single RGB Images Using a Context Preserver Convolutional Neural Network Trained by Multiple Adversarial Examples." IEEE Transactions on Image Processing (2019). ⭐️⭐️
•Color Constancy: Sidorov, Oleksii. "Conditional GANs for Multi-Illuminant Color Constancy: Revolution or Yet Another Approach?." CVPR workshop, 2019. ⭐️⭐️
•DSDNet: Zheng, Quanlong, et al. "Distraction-aware Shadow Detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️⭐️
•ARGAN: Ding, Bin, et al. "ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal." In ICCV, (2019). ⭐️⭐️⭐️
圖像修復
•DRRN: Tai, Ying, Jian Yang, and Xiaoming Liu. "Image super-resolution via deep recursive residual network." The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. ⭐️⭐️⭐️⭐️
•DID-MDN: Zhang, He, and Vishal M. Patel. "Density-aware Single Image De-raining using a Multi-stream Dense Network." arXiv preprint arXiv:1802.07412 (2018). ⭐️⭐️
•IDN: Hui, Zheng, Xiumei Wang, and Xinbo Gao. "Fast and Accurate Single Image Super-Resolution via Information Distillation Network." In CVPR. 2018. ⭐️⭐️⭐️
•SFT-GAN: Wang, X., Yu, K., Dong, C., & Loy, C. C. (2018). Recovering realistic texture in image super-resolution by deep spatial feature transform. In CVPR. 2018. ⭐️⭐️⭐️
•Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring：Nah, Seungjun, Tae Hyun Kim, and Kyoung Mu Lee. "Deep multi-scale convolutional neural network for dynamic scene deblurring." In CVPR, 2017. ⭐️⭐️⭐️
•Enhanced Deep Residual Networks for Single Image Super-Resolution: Lim, Bee, et al. "Enhanced deep residual networks for single image super-resolution." The CVPR workshops, 2017. ⭐️
•AGAN for Raindrop Removal: Qian, Rui, et al. "Attentive Generative Adversarial Network for Raindrop Removal from A Single Image." In CVPR. 2018. ⭐️⭐️⭐️⭐️⭐️
•DCPDN: Zhang, He, and Vishal M. Patel. "Densely connected pyramid dehazing network." In CVPR, 2018. ⭐️⭐️⭐️
•GFN: Ren, W., Ma, L., Zhang, J., Pan, J., Cao, X., Liu, W., & Yang, M. H. (2018). Gated fusion network for single image dehazing. In CVPR, 2018. ⭐️⭐️⭐️⭐️
•SIDCGAN: Li, Runde, et al. "Single Image Dehazing via Conditional Generative Adversarial Network." In CVPR, 2018. ⭐️⭐️
•Dehaze Benchmark: Li, Boyi, et al. "Benchmarking Single Image Dehazing and Beyond." IEEE Transactions on Image Processing (2018). ⭐️⭐️⭐️⭐️⭐️
•Cityscapes + Haze: Sakaridis, Christos, Dengxin Dai, and Luc Van Gool. "Semantic foggy scene understanding with synthetic data." International Journal of Computer Vision (2018): 1-20. ⭐️⭐️⭐️⭐️⭐️
•RESCAN: Li, Xia, et al. "Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining." European Conference on Computer Vision. Springer, Cham, 2018. ⭐️⭐️⭐️
•UD-GAN: Jin, Xin, et al. "Unsupervised Single Image Deraining with Self-supervised Constraints." arXiv preprint arXiv:1811.08575 (2018). ⭐️⭐️⭐️⭐️⭐️
•Deep Tree-Structured Fusion Model: Fu, Xueyang, et al. "A Deep Tree-Structured Fusion Model for Single Image Deraining." arXiv preprint arXiv:1811.08632 (2018). ⭐️⭐️
•Dual CNN: Pan, J., Liu, S., Sun, D., Zhang, J., Liu, Y., Ren, J., ... & Yang, M. H. Learning Dual Convolutional Neural Networks for Low-Level Vision. In CVPR, 2018 (pp. 3070-3079). ⭐️⭐️⭐️
•RAM: Kim, Jun-Hyuk, et al. "RAM: Residual Attention Module for Single Image Super-Resolution." arXiv preprint arXiv:1811.12043 (2018). ⭐️⭐️⭐️
•DNSR (Bi-cycle GAN): Zhao, Tianyu, et al. "Unsupervised Degradation Learning for Single Image Super-Resolution." arXiv preprint arXiv:1812.04240 (2018). ⭐️⭐️⭐️⭐️⭐️
•Cycle-Defog2Refog：Liu, Wei, et al. "End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks." arXiv preprint arXiv:1902.01374 (2019). ⭐️⭐️
•SPANet：Tianyu Wang, Xin Yang, Ke Xu, Shaozhe Chen, Qiang Zhang, Rynson W.H. Lau. "Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset." In CVPR 2019. ⭐️⭐️⭐️⭐️
•remove rain streaks and rain accumulation：Ruoteng Li, Loong-Fah Cheong, and Robby T. Tan. "Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning." In CVPR 2019. ⭐️⭐️⭐️⭐️⭐️
•Rain O’er Me: Huangxing Lin, Yanlong Li, Xinghao Ding, Weihong Zeng, Yue Huang, John Paisley: "Rain O’er Me: Synthesizing real rain to derain with data distillation." arXiv preprint arXiv:1904.04605 (2019). ⭐️⭐️⭐️⭐️
•RNAN: Zhang, Y., Li, K., Li, K., Zhong, B., & Fu, Y. (2019). Residual Non-local Attention Networks for Image Restoration. arXiv preprint arXiv:1903.10082. ⭐️⭐️⭐️⭐️⭐️
•Perceptual GAN loss + TV loss：Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., ... & Shi, W. (2017). Photo-realistic single image super-resolution using a generative adversarial network. In CVPR (pp. 4681-4690).(code) ⭐️⭐️⭐️⭐️⭐️
•PReNet: Ren, Dongwei, et al. "Progressive Image Deraining Networks: A Better and Simpler Baseline." In CVPR, 2019. ⭐️⭐️⭐️
•Zoom to Learn, Learn to Zoom: Zhang, Xuaner, et al. "Zoom to Learn, Learn to Zoom." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️⭐️
•Derain Beachmark: Li, Siyuan, et al. "Single image deraining: A comprehensive benchmark analysis." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️
•Dual residual block: Liu, Xing, et al. "Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️
•Semi-supervised Transfer Learning for Image Rain Removal: Wei, Wei, et al. "Semi-Supervised Transfer Learning for Image Rain Removal." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️⭐️
•UMRL：Yasarla, Rajeev, and Vishal M. Patel. "Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining." CVPR 2019. ⭐️⭐️⭐️⭐️
•NASNet: Qin, Xu, and Zhilin Wang. "NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining." arXiv preprint arXiv:1912.03151 (2019). ⭐️⭐️⭐️⭐️
圖像合成
•Let there be Color!: Iizuka, Satoshi, Edgar Simo-Serra, and Hiroshi Ishikawa. "Let there be color!: joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification." ACM Transactions on Graphics (TOG) 35.4 (2016): 110. ⭐️⭐️⭐️⭐️⭐️
•Colorful Image Colorization: Zhang, Richard, Phillip Isola, and Alexei A. Efros. "Colorful image colorization." European Conference on Computer Vision. Springer, Cham, 2016. ⭐️⭐️⭐️⭐️
•Neural Style: Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arXiv preprint arXiv:1508.06576 (2015). ⭐️⭐️⭐️⭐️⭐️
•Texture Synthesis: Gatys, Leon, Alexander S. Ecker, and Matthias Bethge. "Texture synthesis using convolutional neural networks." Advances in Neural Information Processing Systems. 2015. ⭐️⭐️⭐️⭐️
•Semantic Annotation Artwork: Champandard, Alex J. "Semantic style transfer and turning two-bit doodles into fine artworks." arXiv preprint arXiv:1603.01768 (2016). ⭐️⭐️⭐️
•MRC+CNN Image Synthesis: Li, Chuan, and Michael Wand. "Combining markov random fields and convolutional neural networks for image synthesis." In CVPR. 2016. ⭐️⭐️⭐️⭐️
•More Experiments on Neural Style: Novak, Roman, and Yaroslav Nikulin. "Improving the neural algorithm of artistic style." arXiv preprint arXiv:1605.04603 (2016). ⭐️⭐️
•Deep Photo Style Transfer: Luan, Fujun, et al. "Deep photo style transfer." In CVPR. 2017. ⭐️⭐️⭐️⭐️⭐️
計算影像
•Multi-Illumination Dataset: Murmann, Lukas, et al. "A Dataset of Multi-Illumination Images in the Wild." Proceedings of the IEEE International Conference on Computer Vision. 2019. ⭐️⭐️⭐️⭐️⭐️
•WESPE: Ignatov, Andrey, et al. "WESPE: weakly supervised photo enhancer for digital cameras." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2018. ⭐️⭐️⭐️
GAN
•GAN: Goodfellow, Ian, et al. "Generative adversarial nets." In NIPS. 2014. ⭐️⭐️⭐️⭐️⭐️
•cGAN: Mirza, Mehdi, and Simon Osindero. "Conditional generative adversarial nets." arXiv preprint arXiv:1411.1784 (2014). ⭐️⭐️⭐️⭐️⭐️
•Image-to-Image Translation with Conditional Adversarial Networks: Isola, Phillip, et al. "Image-to-image translation with conditional adversarial networks." arXiv preprint (2017). ⭐️⭐️⭐️⭐️⭐️
•cycleGAN：Zhu, Jun-Yan, et al. "Unpaired image-to-image translation using cycle-consistent adversarial networks." arXiv preprint (2017). ⭐️⭐️⭐️⭐️⭐️
•StartGAN: Choi, Yunjey, et al. "Stargan: Unified generative adversarial networks for multi-domain image-to-image translation." In CVPR 2018. ⭐️⭐️⭐️⭐️
•E-GAN: Wang, C., Xu, C., Yao, X., & Tao, D. (2018). Evolutionary Generative Adversarial Networks. arXiv preprint arXiv:1803.00657. ⭐️⭐️⭐️⭐️
•DCGAN: Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015). ⭐️⭐️⭐️⭐️
•GANtruth：Bujwid, Sebastian, et al. "GANtruth-an unpaired image-to-image translation method for driving scenarios." arXiv preprint arXiv:1812.01710 (2018). ⭐️⭐️⭐️
AR/VR
•Indoor Lighting Estimation: Garon, Mathieu, et al. "Fast Spatially-Varying Indoor Lighting Estimation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️
Person Re-ID
•IANet: Hou, Ruibing, et al. "Interaction-And-Aggregation Network for Person Re-Identification." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️⭐️⭐️
•AlignedReID: Zhang, Xuan, et al. "AlignedReID: Surpassing human-level performance in person re-identification." arXiv preprint arXiv:1711.08184 (2017). ⭐️⭐️⭐️⭐️⭐️
知識抽取
•Knowledge Distillation: Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531. ⭐️⭐️⭐️⭐️⭐️
•Deep Mutual Learning: Zhang, Ying, et al. "Deep mutual learning." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. ⭐️⭐️⭐️⭐️⭐️
•Cooperative learning: Batra, Tanmay, and Devi Parikh. "Cooperative learning with visual attributes." arXiv preprint arXiv:1705.05512 (2017). ⭐️⭐️⭐️
•Deeply-supervised Knowledge Synergy: Sun, D., Yao, A., Zhou, A., & Zhao, H. (2019). Deeply-supervised Knowledge Synergy. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 6997-7006).⭐️⭐️⭐️⭐️⭐️
•ONE: Lan, Xu, Xiatian Zhu, and Shaogang Gong. "Knowledge distillation by On-the-fly Native Ensemble." Proceedings of the 32nd International Conference on Neural Information Processing Systems. Curran Associates Inc., 2018. ⭐️⭐️⭐️⭐️⭐️
•Segmentation Distillation: Liu, Yifan, et al. "Structured Knowledge Distillation for Semantic Segmentation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. ⭐️⭐️⭐️⭐️
不確定性
•aleatoric uncertainty and epistemic uncertainty: Kendall, Alex, and Yarin Gal. "What uncertainties do we need in bayesian deep learning for computer vision?." Advances in neural information processing systems. 2017. ⭐️⭐️⭐️⭐️⭐️
•Learning Model Confidence：Charles Corbière, Nicolas Thome, Avner Bar-Hen, Matthieu Cord, Patrick Pérez. "Addressing Failure Prediction by Learning Model Confidence" NeurIPS, 2019. ⭐️⭐️⭐️⭐️
傳統方法
•Rolling Guidance Filter: Zhang, Q., Shen, X., Xu, L., & Jia, J. Rolling guidance filter. In ECCV, 2014. ⭐️⭐️⭐️⭐️⭐️
閱讀更多 深度學習與NLP 的文章
