DL之DeepLabv1:DeepLabv1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
DL之DeepLabv1:DeepLabv1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
DeepLabv1算法的簡介(論文介紹)
0、實驗結果
1、FCN局限性及其改進
DeepLabv1算法的架構詳解
DeepLabv1算法的案例應用
?
?
?
?
相關文章
DL之DeepLabv1:DeepLabv1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DeepLabv1:DeepLabv1算法的架構詳解
DL之DeepLabv2:DeepLab v2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DeepLabv2:DeepLab v2算法的架構詳解
DL之DeepLabv3:DeepLab v3和DeepLab v3+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DeepLabv3:DeepLab v3和DeepLab v3+算法的架構詳解
DeepLabv1算法的簡介(論文介紹)
? ? ? 作者意識到FCN算法模型的局限性,因此,通過改進提出了DeepLabv1算法。
ABSTRACT ?
? ? ? ?Deep Convolutional Neural Networks (DCNNs) have recently shown state of the ?art performance in high level vision tasks, such as image classification and object ?detection. This work brings together methods from DCNNs and probabilistic ?graphical models for addressing the task of pixel-level classification (also called ?”semantic image segmentation”). We show that responses at the final layer of ?DCNNs are not sufficiently localized for accurate object segmentation. This is ?due to the very invariance properties that make DCNNs good for high level tasks. ?We overcome this poor localization property of deep networks by combining the ?responses at the final DCNN layer with a fully connected Conditional Random ?Field (CRF). Qualitatively, our “DeepLab” system is able to localize segment ?boundaries at a level of accuracy which is beyond previous methods. Quantitatively, ?our method sets the new state-of-art at the PASCAL VOC-2012 semantic ?image segmentation task, reaching 71.6% IOU accuracy in the test set. We show ?how these results can be obtained efficiently: Careful network re-purposing and a ?novel application of the ’hole’ algorithm from the wavelet community allow dense ?computation of neural net responses at 8 frames per second on a modern GPU.
? ? ? ?深度卷積神經網絡(DCNNs)最近在圖像分類和目標檢測等高級視覺任務中表現出了最先進的性能。這項工作結合了DCNNs和概率圖形模型的方法來解決像素級分類(也稱為“語義圖像分割”)的任務。結果表明,對于精確的目標分割,DCNNs最后一層的響應沒有得到足夠的局部化。這是由于非常不變性的性質,使DCNNs適合高級任務。通過將DCNN最后一層的響應與完全連接的條件隨機場(CRF)相結合,克服了深度網絡的這種較差的定位特性。定性地說,我們的“DeepLab”系統能夠以超出以往方法的精度水平定位段邊界。量化地來說,我們的方法集新技術發展水平在PASCAL VOC-2012 語義圖像分割任務,測試集的準確性達到71.6%的IOU。我們展示了可有效地獲得這些結果:仔細的網絡重新設計和一個新的應用小波社區的“孔”算法允許在現代GPU上以每秒8幀的速度密集計算神經網絡響應。
DISCUSSION ?
? ? ? ?Our work combines ideas from deep convolutional neural networks and fully-connected conditional ?random fields, yielding a novel method able to produce semantically accurate predictions and detailed ?segmentation maps, while being computationally efficient. Our experimental results show that ?the proposed method significantly advances the state-of-art in the challenging PASCAL VOC 2012 ?semantic image segmentation task. ?There are multiple aspects in our model that we intend to refine, such as fully integrating its two ?main components (CNN and CRF) and train the whole system in an end-to-end fashion, similar to ?Krahenb ¨ uhl & Koltun (2013); Chen et al. (2014); Zheng et al. (2015). We also plan to experiment ¨ ?with more datasets and apply our method to other sources of data such as depth maps or videos. Recently, ?we have pursued model training with weakly supervised annotations, in the form of bounding ?boxes or image-level labels (Papandreou et al., 2015). ?At a higher level, our work lies in the intersection of convolutional neural networks and probabilistic ?graphical models. We plan to further investigate the interplay of these two powerful classes of ?methods and explore their synergistic potential for solving challenging computer vision tasks.
? ? ? ?我們的工作結合了深卷積神經網絡和全連通條件隨機場的思想,提出了一種新的方法,能夠產生語義準確的預測和詳細的分割地圖,同時計算效率高。實驗結果表明,該方法顯著提高了PASCAL VOC 2012語義圖像分割的水平。我們的模型中有很多方面是我們想要完善的,比如充分集成其兩個主要組件(CNN和CRF),以端到端的方式訓練整個系統,類似于Krahenb¨uhl & Koltun (2013);Chen等(2014);鄭等(2015)。我們還計劃用更多的數據集進行實驗,并將我們的方法應用于其他數據源,如深度地圖或視頻。最近,我們以邊界框或圖像級標簽的形式,采用弱監督注解進行模型訓練(Papandreou et al., 2015)。在更高層次上,我們的工作是卷積神經網絡和概率圖形模型的交叉。我們計劃進一步研究這兩種功能強大的方法之間的相互作用,并探索它們在解決具有挑戰性的計算機視覺任務方面的協同潛力。
?
?
論文
Liang-ChiehChen, George Papandreou, IasonasKokkinos, Kevin Murphy, Alan L. Yuille.
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs, ICCV, 2015.
https://arxiv.org/abs/1412.7062
0、實驗結果
1、在Titan GPU 上運行速度達到了8FPS,全連接CRF 平均推斷需要0.5s
2、與最先進的模型在valset的比較
Comparisons with state-of-the-art models on the valset
First row: images.?第一行:圖像
Second row: ground truths.?第二行:基本真理
Third row: other recent models (Left: FCN-8s, Right: TTI-Zoomout-16).其他最新型模型(左:FCN-8s,右:TTI-Zoomout-16)
Fourth row: our DeepLab-CRF.??我們的Deeplab CRF
3、VOC 2012 VAL可視化結果
Visualization results on VOC 2012-val
? ? ? For each row, we show the input image, the segmentation result delivered by the DCNN (DeepLab), and the refined segmentation result of the Fully Connected CRF (DeepLab-CRF).對于每一行,我們顯示輸入圖像,DCNN (DeepLab)提供的分割結果,以及完全連接的CRF (DeepLab-CRF)的細化分割結果。
failure modes 失敗的模型
?
?
?
1、FCN局限性及其改進
1、FCN局限性分析
- 池化層可增大神經元的感受野,提高分類精度,但導致特征圖分辨率降低
- 倍率過大的上采樣導致FCN的分割邊界模糊
2、改進FCN
- –仍以VGG-16為基礎
- –刪去部分池化層(感受野變小)
- –利用預訓練的VGG-16在新網絡上進行網絡微調
- –用帶孔卷積(膨脹卷積)替換傳統卷積(增大感受野,同時提升特征圖的分辨率)
- –利用全連接條件隨機場提升分割邊界的精度
- –利用多尺度特征
?
?
DeepLabv1算法的架構詳解
更新……
?
?
?
?
?
?
DeepLabv1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DeepLabv1:DeepLabv1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。
- 上一篇: DL之U-Net:U-Net算法的简介(
- 下一篇: DL之DeepLabv2:DeepLab