DL之GCN：GCN算法的簡介(論文介紹)、架構詳解、案例應用等配圖集合之詳細攻略

?

?

目錄

GCN算法的簡介(論文介紹)

0、實驗結果

GCN算法的架構詳解

GCN算法的案例應用

---

?

?

?

?

相關文章
DL之GCN：GCN算法的簡介(論文介紹)、架構詳解、案例應用等配圖集合之詳細攻略
DL之GCN：GCN算法的架構詳解

?

GCN算法的簡介(論文介紹)

? ? ? 作者在該論文中，強調了Large Kernel的重要性。

Abstract ?
? ? ? ?One of recent trends [30, 31, 14] in network architecture ?design is stacking small filters (e.g., 1x1 or 3x3) in the ?entire network because the stacked small filters is more efficient ?than a large kernel, given the same computational ?complexity. However, in the field of semantic segmentation, ?where we need to perform dense per-pixel prediction, ?we find that the large kernel (and effective receptive field) ?plays an important role when we have to perform the classification ?and localization tasks simultaneously. Following ?our design principle, we propose a Global Convolutional ?Network to address both the classification and localization ?issues for the semantic segmentation. We also suggest a ?residual-based boundary refinement to further refine the object ?boundaries. Our approach achieves state-of-art performance ?on two public benchmarks and significantly outperforms ?previous results, 82.2% (vs 80.2%) on PASCAL VOC ?2012 dataset and 76.9% (vs 71.8%) on Cityscapes dataset.
? ? ? ?最近網絡架構設計的一個趨勢是在整個網絡中堆疊小過濾器(例如1x1或3x3)，因為在相同的計算復雜度下，堆疊小過濾器比大型內核更有效。然而，在語義分割領域，我們需要進行密集的逐像素預測，我們發現，當我們必須同時執行分類和定位任務時，大核(有效接受域)發揮著重要作用。根據我們的設計原則，我們提出了一個全局卷積網絡來解決語義分割的分類和定位問題。我們還建議基于殘差的邊界細化來進一步細化對象邊界。我們的方法在兩個公共基準上實現了最先進的性能，并顯著優于之前的結果，分別是PASCAL VOC 2012數據集的82.2% (vs . 80.2%)和Cityscapes數據集的76.9% (vs . 71.8%)。
Conclusion ?
? ? ? ?According to our analysis on classification and segmentation, ?we find that large kernels is crucial to relieve the ?contradiction between classification and localization. Following ?the principle of large-size kernels, we propose the ?Global Convolutional Network. The ablation experiments ?show that our proposed structures meet a good trade-off ?between valid receptive field and the number of parameters, ?while achieves good performance. To further refine ?the object boundaries, we present a novel Boundary Refinement ?block. Qualitatively, our Global Convolutional ?Network mainly improve the internal regions while Boundary ?Refinement increase performance near boundaries. Our ?best model achieves state-of-the-art on two public benchmarks: ?PASCAL VOC 2012 (82.2%) and Cityscapes ?(76.9%).
? ? ? ?通過對分類和分割的分析，我們發現大內核對于緩解分類和定位之間的矛盾至關重要。根據大內核的原理，我們提出了全球卷積網絡。腐蝕實驗表明，我們提出的結構在有效接受域和參數之間達到了很好的平衡，同時取得了較好的性能。為了進一步細化對象邊界，我們提出了一種新的邊界細化塊。在質量上，我們的全局卷積網絡主要是對內部區域進行改進，而邊界細化則提高了邊界附近的性能。我們最好的模型達到了最先進的兩個公共基準:帕斯卡VOC 2012(82.2%)和城市景觀(76.9%)。

論文
Chao Peng, XiangyuZhang, Gang Yu, GuimingLuo, Jian Sun.
Large Kernel Matters ——
Improve Semantic Segmentation by Global Convolutional Network. CVPR 2017.
https://arxiv.org/abs/1703.02719

?

0、實驗結果

1、PASCAL VOC 2012 validation set

2、PASCAL VOC 2012和ImageNet

standard benchmark：PASCAL VOC 2012 and Cityscapes? ??標準基準:2012年PASCAL VOC和Cityscapes?
ResNet152 (pretrained on ImageNet) as the base model for fine tuning.??ResNet152(在ImageNet上預訓練)作為微調的基本模型。

3、Examples of semantic segmentation results on PASCAL VOC 2012

4、Examples of semantic segmentation results on Cityscapes

?

?

GCN算法的架構詳解

更新……

?

?

GCN算法的案例應用

更新……

?

?

?

總結

以上是生活随笔為你收集整理的DL之GCN：GCN算法的简介(论文介绍)、架构详解、案例应用等配图集合之详细攻略的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。