オートエンコーダーと異常検知入門

 オートエンコーダーと異常検知入門

「実践者向けディープラーニング勉強会 第四回」に向けた資料。
https://dl4-practitioners.connpass.com/event/132618/

オートエンコーダー以外の手法も少し触れてます。

590fe37e032309f0f2657135085e395d?s=128

kmotohas

June 19, 2019
Tweet

Transcript

  1. 2.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 ‣本橋

    和貴 @kmotohas - スカイマインド株式会社 • Deep Learning Engineer (前職ではDL+ROS) - 素粒⼦物理学実験(LHC-ATLAS実験)出⾝ • 博⼠(理学) - 好きな定理︓ネーターの定理 2 ࣗݾ঺հ ܥʹ࿈ଓతͳରশੑ͕͋Δ৔߹͸ͦΕʹରԠ͢Δอଘଇ͕ଘࡏ͢Δͱड़΂ΔఆཧͰ͋Δɻ(Wikipedia)
  2. 3.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 3

    ‣ オートエンコーダーとは何か - Convolutional Autoencoder ‣ 異常検知への適⽤ - テーブルデータ - 画像データ ࠓճ࿩͢͜ͱ
  3. 4.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 4

    ΦʔτΤϯίʔμʔͱ͸ IUUQTEFWFMPQFSPSBDMFDPNEBUBCBTFTOFVSBMOFUXPSLNBDIJOFMFBSOJOH IUUQTNFEJVNDPN!DVSJPVTJMZDSFEJUDBSEGSBVEEFUFDUJPOVTJOHBVUPFODPEFSTJOLFSBTUFOTPSqPXGPSIBDLFSTQBSUWJJFDCE ҰൠతͳχϡʔϥϧωοτϫʔΫ ΦʔτΤϯίʔμʔ f(x) = y <latexit sha1_base64="vukw9W0rGZmSt2cyXd3Jlpp4eYk=">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</latexit> f(x) = x <latexit sha1_base64="tBr0KvrUUkvqCjnc8u1rKrjq+Tk=">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</latexit>
  4. 5.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 5

    ΦʔτΤϯίʔμʔͷΠϝʔδ ѹॖ ղౚ தؒͷϘτϧωοΫͰ σʔλͷޮ཰తͳʮදݱʯΛநग़ Πϝʔδ͸ϑΝΠϧͷѹॖɾղౚ "VUPFODPEFS ʹࣗݾූ߸Խث ڭࢣ͕ࣗ෼ࣗ਎ͷ ʮڭࢣͳֶ͠शʯ
  5. 6.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 6

    5FOTPSqPX ,FSBT Ͱͷ࣮૷ྫ ‏ೖྗͱ໨ඪͷग़ྗ͸ͲͪΒ΋܇࿅σʔλͱֶͯ͠श ‏༻͍ΔϞδϡʔϧͷΠϯϙʔτ ‏σʔλͷಡΈࠐΈɺਖ਼نԽ ɹೋ࣍ݩͷը૾ΛҰ࣍ݩͷϕΫτϧʹม׵
  6. 7.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 7

    ςετσʔλͷ෮ݩ ‏ςετσʔλΛҰ࣍ݩϕΫτϧʹͯ͠Ϟσϧʹೖྗ ‏NBUQMPUMJCͰҰຕΊͷը૾ͷ෮ݩ݁ՌΛ֬ೝ ݩσʔλ ෮ݩ͞Εͨσʔλ º͔Β࣍ݩ·Ͱ৘ใѹॖͯ͠΋ σʔλΛ͏·͘෮ݩͰ͖͍ͯΔ ʢූ߸Խͯ͠΋৘ใ͕΄ͱΜͲࣦΘΕ͍ͯͳ͍ʣ
  7. 8.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 8

    $"& $POWPMVUJPOBM"VUP&ODPEFS શ݁߹૚Ͱ͸ͳ͘৞ΈࠐΈ૚Λ༻͍ͨΦʔτΤϯίʔμʔ IUUQTTFpLTDPNDPOWPMVUJPOBMBVUPFODPEFSDMVTUFSJOHJNBHFTXJUIOFVSBMOFUXPSLT
  8. 9.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 9

    ‏.BY1PPMJOH%Ͱը૾αΠζΛখ͘͢͞Δ ‏6Q4BNQMJOH%Ͱը૾αΠζΛେ͖͘͢Δ ,FSBTΛ༻͍ͨ$"&ͷ࣮૷ྫ
  9. 10.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 10

    ,FSBTΛ༻͍ͨ$"&ͷ࣮૷ྫ ‏.BY1PPMJOH%Ͱը૾αΠζΛখ͘͢͞Δ ‏6Q4BNQMJOH%Ͱը૾αΠζΛେ͖͘͢Δ
  10. 12.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 12

    ಉ͡ϞσϧͰ΋͏·͘෮߸Ͱ͖ͳ͍έʔε ܇࿅σʔληοτͱҟͳΔ෼෍ͷσʔλ͸͏·͘෮߸Ͱ͖ͳ͍ ϊΠζ͕৐͍ͬͯͨΓܗ͕ಛघͩͬͨΓ
  11. 13.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 13

    ಉ͡ϞσϧͰ΋͏·͘෮߸Ͱ͖ͳ͍έʔε ܇࿅σʔληοτͱҟͳΔ෼෍ͷσʔλ͸͏·͘෮߸Ͱ͖ͳ͍ ϊΠζ͕৐͍ͬͯͨΓܗ͕ಛघͩͬͨΓ ҟৗݕ஌ʹ࢖͑Δ
  12. 14.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 14

    ҟৗݕ஌λεΫͷྫ %FFQ-FBSOJOHGPS"OPNBMZ%FUFDUJPO"4VSWFZ ಈը ը૾ ࣌ܥྻ ϩά ʢςΩετʣ
  13. 15.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 15

    ‣ 「異常」というくらいなのでデータ数が少ない - ⼀般的に「正常データ数 >> 異常データ数」 ‣ 分類問題として教師あり学習で解くのは難しい ‣ 教師なし学習(もしくは半教師あり学習)で解くことが多い - 正常データのみで学習すると異常データの再構成誤差が⼤きくなることを利⽤ ҟৗݕ஌λεΫͱڭࢣͳֶ͠श
  14. 16.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 16

    ‣ ULB (ブリュッセル⾃由⼤学) 提供のテーブルデータセット - https://www.kaggle.com/mlg-ulb/creditcardfraud ‣ PCAで匿名化された特徴量28個と時間・取引⾦額・正常/不正の⼆値ラベル ΫϨδοτΧʔυෆਖ਼ར༻ݕ஌ͷྫ ॎ࣠ϩάεέʔϧ ਖ਼ৗσʔλʢෆਖ਼σʔλʣͷΈΛ༻͍ͯΦʔτΤϯίʔμʔΛֶश
  15. 17.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 17

    ‣ 以降3ページ、DATASCIENCE.COMのチュートリアルより拝借 - https://www.datascience.com/blog/fraud-detection-with-tensorflow ΦʔτΤϯίʔμʔͷ࣮૷ྫ nb_epoch = 100 batch_size = 128 input_dim = train_x.shape[1] #num of columns, 30 encoding_dim = 14 hidden_dim = int(encoding_dim / 2) #i.e. 7 learning_rate = 1e-7 input_layer = Input(shape=(input_dim, )) encoder = Dense(encoding_dim, activation="tanh", activity_regularizer=regularizers.l1(learning_rate))(input_layer) encoder = Dense(hidden_dim, activation="relu")(encoder) decoder = Dense(hidden_dim, activation='tanh')(encoder) decoder = Dense(input_dim, activation='relu')(decoder) autoencoder = Model(inputs=input_layer, outputs=decoder)
  16. 18.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 18

    ࠶ߏ੒ޡࠩ .4& ͷ෼෍ Reconstruction Error Reconstruction Error Number of Transactions Number of Transactions 0 2 4 6 8 10 0 50 100 150 200 250 ෼෍ܗঢ়͕༏Ґʹҟͳ͍ͬͯΔ‎ᮢ஋ΛܾΊͯਖ਼ৗҟৗ൑ผ IUUQTNFEJVNDPN!DVSJPVTJMZDSFEJUDBSEGSBVEEFUFDUJPOVTJOHBVUPFODPEFSTJOLFSBTUFOTPSqPXGPSIBDLFSTQBSUWJJFDCE
  17. 20.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 20

    .75FD"OPNBMZ%FUFDUJPO%BUBTFU .75FD"% aset of rial ac- ct-free mages dust or le kind evalu- fferent cal in- a 2007 provide es with h class ng and nnota- nerated arance ore, ar- pproxi- aly de- gested give a ct our- meth- initial Figure 2: Example images for all five textures and ten ob- ject categories of the MVTec AD dataset. For each cate- 2.1.2 Segmentation of Anomalous Regions For the evaluation of methods that segment anomalies in images, only very few public datasets are currently avail- able. All of them focus on the inspection of textured sur- faces and, to the best of our knowledge, there does not yet exist a comprehensive dataset that allows for the segmenta- tion of anomalous regions in natural images. Carrera et al. [6] provide NanoTWICE,2 a dataset of 45 gray-scale images that show a nanofibrous material ac- quired by a scanning electron microscope. Five defect-free images can be used for training. The remaining 40 images contain anomalous regions in the form of specks of dust or flattened areas. Since the dataset only provides a single kind of texture, it is unclear how well algorithms that are evalu- ated on this dataset generalize to other textures of different domains. A dataset that is specifically designed for optical in- spection of textured surfaces was proposed during a 2007 DAGM workshop by Wieler and Hahn [28]. They provide ten classes of artificially generated gray-scale textures with defects weakly annotated in the form of ellipses. Each class comprises 1000 defect-free texture patches for training and 150 defective patches for testing. However, their annota- tions are quite coarse and since the textures were generated by very similar texture models, the variance in appearance between the different textures is quite low. Furthermore, ar- tificially generated datasets can only be seen as an approxi- .75FD͸υΠπɾϛϡϯϔϯͷը૾ॲཧιϑτ΢ΣΞ։ൃձࣾ IUUQTXXXNWUFDDPNDPNQBOZSFTFBSDIEBUBTFUT  ຕҎ্ͷҟৗݕ஌༻ը૾σʔληοτΛެ։ छྨͷҟͳΔ෺ମͱςΫενϟͷਖ਼ৗҟৗσʔλΛؚΉ ղઆ࿦จ͸ίϯϐϡʔλϏδϣϯͷτοϓձٞ$713Ͱ࠾୒
  18. 21.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 21

    .75FD"OPNBMZ%FUFDUJPO%BUBTFU .75FD"% Category AE (SSIM) AE (L2) AnoGAN CNN Feature Dictionary Texture Inspection Variation Model Textures Carpet 0.43 0.90 0.57 0.42 0.82 0.16 0.89 0.36 0.57 0.61 - Grid 0.38 1.00 0.57 0.98 0.90 0.12 0.57 0.33 1.00 0.05 - Leather 0.00 0.92 0.06 0.82 0.91 0.12 0.63 0.71 0.00 0.99 - Tile 1.00 0.04 1.00 0.54 0.97 0.05 0.97 0.44 1.00 0.43 - Wood 0.84 0.82 1.00 0.47 0.89 0.47 0.79 0.88 0.42 1.00 - Objects Bottle 0.85 0.90 0.70 0.89 0.95 0.43 1.00 0.06 - 1.00 0.13 Cable 0.74 0.48 0.93 0.18 0.98 0.07 0.97 0.24 - - Capsule 0.78 0.43 1.00 0.24 0.96 0.20 0.78 0.03 - 1.00 0.03 Hazelnut 1.00 0.07 0.93 0.84 0.83 0.16 0.90 0.07 - - Metal nut 1.00 0.08 0.68 0.77 0.86 0.13 0.55 0.74 - 0.32 0.83 Pill 0.92 0.28 1.00 0.23 1.00 0.24 0.85 0.06 - 1.00 0.13 Screw 0.95 0.06 0.98 0.39 0.41 0.28 0.73 0.13 - 1.00 0.10 Toothbrush 0.75 0.73 1.00 0.97 1.00 0.13 1.00 0.03 - 1.00 0.60 Transistor 1.00 0.03 0.97 0.45 0.98 0.35 1.00 0.15 - - Zipper 1.00 0.60 0.97 0.63 0.78 0.40 0.78 0.29 - - Table 2: Results of the evaluated methods when ap- plied to the classification of anomalous images. For each dataset category, the ratio of correctly classified samples of anomaly-free (top row) and anomalous images (bottom ment is not possible for every ob strict the evaluation of this meth (Table 2). We use 30 randomly se each object category in its origin and variance parameters at each p are converted to gray-scale before Anomaly maps are obtained b of each test pixel’s gray value to relative to its predicted standard GMM-based texture inspection, w plementation of the HALCON ma 4.2. Data Augmentation Since the evaluated methods ba are typically trained on large data performed for these methods for b For the texture images, we random lar patches of fixed size from the object category, we apply a random Additional mirroring is applied w We augment each category to crea 4.3. Evaluation Metric Each of the evaluated method spatial map in which large value Regions egment anomalies in ts are currently avail- ction of textured sur- ge, there does not yet ows for the segmenta- mages. WICE,2 a dataset of nofibrous material ac- cope. Five defect-free remaining 40 images m of specks of dust or provides a single kind rithms that are evalu- r textures of different igned for optical in- oposed during a 2007 n [28]. They provide ay-scale textures with of ellipses. Each class tches for training and owever, their annota- xtures were generated ariance in appearance low. Furthermore, ar- be seen as an approxi- pervised anomaly de- s have been suggested ntel et al. [20] give a ork. We restrict our- state-of-the art meth- baseline for our initial works Figure 2: Example images for all five textures and ten ob- ject categories of the MVTec AD dataset. For each cate- gory, the top row shows an anomaly-free image. The middle શମతʹΦʔτΤϯίʔμʔΛ༻͍ͨϞσϧ͕ڧ͍ ্ஈਖ਼ৗσʔλͷਖ਼ղ཰ Լஈҟৗσʔλͷਖ਼ղ཰
  19. 22.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 22

    "& - ͱ"& 44*. ଛࣦؔ਺͸ඞͣࣗ৐ޡࠩͰͳͯ͘͸͍͚ͳ͍Θ͚Ͱ΋ͳ͍ -ޡࠩ ࣗ৐ޡࠩ 44*. 4USVDUVBM4*.JMBSJUZ JOEFY<> Dosovitskiy and Brox (2016). It increases the quality of the produced reconstructions by extracting features from both the input image x and its reconstruction ˆ x and enforc- ing them to be equal. Consider F : Rk⇥h⇥w ! Rf to be a feature extractor that obtains an f-dimensional feature vector from an input image. Then, a regularizer can be added to the loss function of the autoencoder, yielding the feature matching autoencoder (FM-AE) loss LFM(x, ˆ x) = L2(x, ˆ x) + kF(x) F(ˆ x)k2 2 , (3) where > 0 denotes the weighting factor between the two loss terms. F can be parameterized using the first layers of a CNN pretrained on an image classification task. During evaluation, a residual map RFM is obtained by comparing the per-pixel `2-distance of x and ˆ x. The hope is that sharper, more realistic reconstructions will lead to better residual maps compared to a standard `2-autoencoder. 3.1.4. SSIM Autoencoder. We show that employing more elaborate architectures such as VAEs or FM-AEs does not yield satisfactory improvements of the residial maps over deterministic `2-autoencoders in the unsupervised defect segmentation task. They are all based on per-pixel evaluation metrics that assume an unrealistic indepen- dence between neighboring pixels. Therefore, they fail to detect structural differences between the inputs and their l(p, q) = 2µpµq + c1 µ2 p + µ2 q + c1 (5) c(p, q) = 2 p q + c2 2 p + 2 q + c2 (6) s(p, q) = 2 pq + c2 2 p q + c2 . (7) The constants c1 and c2 ensure numerical stability and are typically set to c1 = 0.01 and c2 = 0.03. By substituting (5)-(7) into (4), the SSIM is given by SSIM(p, q) = (2µpµq + c1)(2 pq + c2) (µ2 p + µ2 q + c1)( 2 p + 2 q + c2) . (8) It holds that SSIM(p, q) 2 [ 1, 1]. In particular, SSIM(p, q) = 1 if and only if p and q are identical (Wang et al., 2004). Figure 2 shows the different percep- tions of the three similarity functions that form the SSIM index. Each of the patch pairs p and q has a constant `2- residual of 0.25 per pixel and hence assigns low defect scores to each of the three cases. SSIM on the other hand is sensitive to variations in the patches’ mean, variance, and covariance in its respective residual map and assigns low similarity to each of the patch pairs in one of the comparison functions. training them purely on defect-free image data. During testing, the autoencoder will fail to reconstruct defects that have not been observed during training, which can thus be segmented by comparing the original input to the recon- struction and computing a residual map R(x, ˆ x) 2 Rw⇥h. 3.1.1. `2-Autoencoder. To force the autoencoder to recon- struct its input, a loss function must be defined that guides it towards this behavior. For simplicity and computational speed, one often chooses a per-pixel error measure, such as the L2 loss L2(x, ˆ x) = h 1 X r=0 w 1 X c=0 (x(r, c) ˆ x(r, c))2 , (2) where x(r, c) denotes the intensity value of image x at the pixel (r, c). To obtain a residual map R`2 (x, ˆ x) during evaluation, the per-pixel `2-distance of x and ˆ x is com- puted. 3.1.2. Variational Autoencoder. Various extensions to the deterministic autoencoder framework exist. VAEs (Kingma and Welling, 2014) impose constraints on the latent variables to follow a certain distribution z ⇠ P(z). For simplicity, the distribution is typically chosen to be ਓ͕ؒײ͡Δҧ͍ ɹɾըૉ஋ ً౓஋ ͷมԽ ɹɾίϯτϥετͷมԽ ɹɾߏ଄ͷมԽ ͕ූ߸ԽલޙͰͲΕ͘Β͍มԽ͔ͨ͠Λද͢ࢦඪ ʢը૾Λখ͍͞8JOEPXʹ෼͚ͯܭࢉʣ IUUQWJTVBMJ[FIBUFOBCMPHDPNFOUSZ IUUQTEGUBMLKQ Q
  20. 23.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 23

    "OP("/<> To be published in the proceedings of IPMI 2017 Fig. 2. (a) Deep convolutional generative adversarial network. (b) t-SNE embedding of normal (blue) and anomalous (red) images on the feature representation of the last convolution layer (orange in (a)) of the discriminator. 2.1 Unsupervised Manifold Learning of Normal Anatomical Variability ("/Λਖ਼ৗσʔλͰ܇࿅͠ɺਖ਼ৗσʔλͷੜ੒Ϟσϧʢ֬཰෼෍ʣΛߏங IUUQTBSYJWPSHBCT
  21. 24.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 24

    $//'FBUVSF%JDUJPOBSZ<> and outputs the best k clusters and corresponding k centroids. A centroid is the mean position of all the elements of the cluster. For each cluster, we take the feature vector that is nearest to its centroid. The set of these k feature vectors compose the dictionary W. Figure 4 shows the pipeline for dictionary building. Figure 5 shows examples of dictionaries learned from images of the training set (anomaly free) with different patch sizes and number of clusters. The figure shows the subregions corresponding to each feature vector of the dictionary W. Figure 4. Examples of dictionary achieved considering different patch sizes and different number of subregions. QBUDI@TJ[FY TUSJEF 3FT/FU EJNBWHQPPMMBZFS ৘ใྔ LNFBOT ʢΫϥελத৺ʹҰ൪͍ۙ ϕΫτϧΛબ୒ʣ ಛ௃ྔϕΫτϧͷσΟΫγϣφϦͷதͰޓ͍ͷڑ཭͕͋Δᮢ஋ΑΓԕ͍ϕΫτϧΛҟৗྖҬͱ͢Δ ࣍ݩ࡟ݮΛߦͳ͍ͬͯΔ෦෼ IUUQTXXXODCJOMNOJIHPWQVCNFE
  22. 25.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 25

    .75FD"OPNBMZ%FUFDUJPO%BUBTFU .75FD"% Category AE (SSIM) AE (L2) AnoGAN CNN Feature Dictionary Texture Inspection Variation Model Textures Carpet 0.43 0.90 0.57 0.42 0.82 0.16 0.89 0.36 0.57 0.61 - Grid 0.38 1.00 0.57 0.98 0.90 0.12 0.57 0.33 1.00 0.05 - Leather 0.00 0.92 0.06 0.82 0.91 0.12 0.63 0.71 0.00 0.99 - Tile 1.00 0.04 1.00 0.54 0.97 0.05 0.97 0.44 1.00 0.43 - Wood 0.84 0.82 1.00 0.47 0.89 0.47 0.79 0.88 0.42 1.00 - Objects Bottle 0.85 0.90 0.70 0.89 0.95 0.43 1.00 0.06 - 1.00 0.13 Cable 0.74 0.48 0.93 0.18 0.98 0.07 0.97 0.24 - - Capsule 0.78 0.43 1.00 0.24 0.96 0.20 0.78 0.03 - 1.00 0.03 Hazelnut 1.00 0.07 0.93 0.84 0.83 0.16 0.90 0.07 - - Metal nut 1.00 0.08 0.68 0.77 0.86 0.13 0.55 0.74 - 0.32 0.83 Pill 0.92 0.28 1.00 0.23 1.00 0.24 0.85 0.06 - 1.00 0.13 Screw 0.95 0.06 0.98 0.39 0.41 0.28 0.73 0.13 - 1.00 0.10 Toothbrush 0.75 0.73 1.00 0.97 1.00 0.13 1.00 0.03 - 1.00 0.60 Transistor 1.00 0.03 0.97 0.45 0.98 0.35 1.00 0.15 - - Zipper 1.00 0.60 0.97 0.63 0.78 0.40 0.78 0.29 - - Table 2: Results of the evaluated methods when ap- plied to the classification of anomalous images. For each dataset category, the ratio of correctly classified samples of anomaly-free (top row) and anomalous images (bottom ment is not possible for every ob strict the evaluation of this meth (Table 2). We use 30 randomly se each object category in its origin and variance parameters at each p are converted to gray-scale before Anomaly maps are obtained b of each test pixel’s gray value to relative to its predicted standard GMM-based texture inspection, w plementation of the HALCON ma 4.2. Data Augmentation Since the evaluated methods ba are typically trained on large data performed for these methods for b For the texture images, we random lar patches of fixed size from the object category, we apply a random Additional mirroring is applied w We augment each category to crea 4.3. Evaluation Metric Each of the evaluated method spatial map in which large value Regions egment anomalies in ts are currently avail- ction of textured sur- ge, there does not yet ows for the segmenta- mages. WICE,2 a dataset of nofibrous material ac- cope. Five defect-free remaining 40 images m of specks of dust or provides a single kind rithms that are evalu- r textures of different igned for optical in- oposed during a 2007 n [28]. They provide ay-scale textures with of ellipses. Each class tches for training and owever, their annota- xtures were generated ariance in appearance low. Furthermore, ar- be seen as an approxi- pervised anomaly de- s have been suggested ntel et al. [20] give a ork. We restrict our- state-of-the art meth- baseline for our initial works Figure 2: Example images for all five textures and ten ob- ject categories of the MVTec AD dataset. For each cate- gory, the top row shows an anomaly-free image. The middle શମతʹΦʔτΤϯίʔμʔΛ༻͍ͨϞσϧ͕ڧ͍ ্ஈਖ਼ৗσʔλͷਖ਼ղ཰ Լஈҟৗσʔλͷਖ਼ղ཰
  23. 26.

    Kazuki Motohashi - Skymind K.K. 実践者向けディープラーニング勉強会 第4回 - 19/June/2019 26

    ‣ オートエンコーダーは⼊⼒と⽬的の出⼒に同じデータを⽤いてデータの 効率的な「表現」を学習 ‣ Max Pooling - Up Sampling を⽤いて畳み込み層を⽤いたオートエン コーダーも実現できる ‣ 再構成誤差を指標に教師なし学習で異常検知を⾏うことができる ‣ 「再構成誤差」の定義は⾊々ある ‣ MVTec AD データセットは実⽤的に⾯⽩そう ·ͱΊ