感兴趣的论文

[ghost]

另一个清单 https://www.yuque.com/lart/papers/list

[ghost]

Segmentation

• [x] Large Kernel Matters——Improve Semantic Segmentation by Global Convolutional Network
• [x] DFN: Learning a Discriminative Feature Network for Semantic Segmentation
• [ ] BiSeNet: BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
• [ ] RFB: Receptive Field Block Net for Accurate and Fast Object Detection
• [ ] DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

[lartpang]

Segmentaon

• [x] FCN https://arxiv.org/abs/1411.4038
• [x] SegNet https://arxiv.org/abs/1511.00561
• [x] Deeplab https://arxiv.org/pdf/1606.00915.pdf
• [x] U‐Net https://arxiv.org/abs/1505.04597
• [x] RefineNet https://arxiv.org/abs/1611.06612
• [x] PSPNet https://arxiv.org/abs/1612.01105
• [ ] Mask‐RCNN https://arxiv.org/abs/1703.06870

Saliency

• [x] DHS http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Liu_DHSNet_Deep_Hierarchical_CVPR_2016_paper.pdf
• [x] RFCN https://www.researchgate.net/profile/Pingping_Zhang6/publication/308278832_Saliency_Detection_with_Recurrent_Fully_Convolutional_Networks/links/584b5da208aecb6bd8c157e0/Saliency-Detection-with-Recurrent-Fully-Convolutional-Networks.pdf
• [x] DSS https://arxiv.org/abs/1611.04849
• [ ] Amulet https://arxiv.org/abs/1708.02001
• [ ] SRM https://pan.baidu.com/s/121DI1U9sqNEsfuVFOO22qA

补充

• [ ] Recurrent Attentional Networks for Saliency Detection

[lartpang]

GNN

• [ ] Situation Recognition with Graph Neural Networks
• [ ] SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation
• [x] Semantic Object Parsing with Graph LSTM
• [x] Interpretable Structure-Evolving LSTM

[powerws]

您好，我运营了一个论文笔记分享的公众号，目前刚在运行，可以转载您的论文笔记吗，确实没有钱，给您啥报酬，只是想建立一个共享社区

[powerws]

我的联系方式：QQ:2509058483 微信号公众号：深度学习社区DLC

[lartpang]

@powerws 欢饮转载，遵守https://creativecommons.org/licenses/by-nc-sa/4.0/deed.zh即可。这也都是平时的一些记录，我暂时也没工夫进一步整理。觉得有用可以转载哦。

[powerws]

谢谢您

发自我的iPhone

------------------ 原始邮件 ------------------ 发件人: MY_ <[email protected]> 发送时间: 2020年4月21日 19:20 收件人: lartpang/Machine-Deep-Learning <[email protected]> 抄送: powerws <[email protected]>, Mention <[email protected]> 主题: 回复：[lartpang/Machine-Deep-Learning] 感兴趣的论文 (#53)

@powerws 欢饮转载，遵守https://creativecommons.org/licenses/by-nc-sa/4.0/deed.zh即可。这也都是平时的一些记录，我暂时也没工夫进一步整理。觉得有用可以转载哦。

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.