Paper-Survey: Objects as Points

F48d3107f5e7a4c6f765752df9754e6b?s=47 fam_taro
April 19, 2019

Paper-Survey: Objects as Points

F48d3107f5e7a4c6f765752df9754e6b?s=128

fam_taro

April 19, 2019
Tweet

Transcript

  1. 4.

    ಛ௃ • ෺ମݕग़Ϟσϧ • ༗໊ͳྫ: SSD, YOLOv3, Re.naNet, M2Det... •

    ݕग़ͷΈͳΒͣ࢟੎ɾdepthɾ޲͖ɾ3d size ౳ʹ΋ద༻͍ͯ͠Δ • backbone ͱͯ͠ DLA(deep layers aggrega.on) ΍ Hourglass(CornerNet ౳Ͱ࢖ ༻) Λ࢖༻ 4
  2. 5.

    ಛ௃ • bounding box Λ࢖Θͣʹݕग़Λߦ͏Ϟσϧ(keypointਪఆ) • bounding box ༻ͷ grid

    ͷ୅ΘΓʹ໨͕ࡉ͔͍ heatmap(H, W Λ4Ͱׂͬͨఔ ౓ͷ΋ͷ) Λग़ྗ • heatmap ͕ߴ͍৔ॴ(௖఺) Λ෺ମͷத৺ͱਪఆ • த৺ͱͳΔ৔ॴͷ feature ͔Β෺ମͷେ͖͞ɾ཭ࢄԽޡࠩΛਪఆ • ཭ࢄԽޡࠩ = heatmap ʹͨ͠ࡍͷޡࠩ • େ͖͞ʹ͍ͭͯ͸ scale ͍ͯ͠ͳ͍(ͦͷ··ͷ஋) 5
  3. 6.

    ಛ௃ • ༧ଌϘοΫε = heatmap ͷ࠲ඪ + ༧ଌϘοΫεαΠζ + ༧ଌ཭ࢄԽޡࠩ

    • ֶशʹ࢖͏ heatmap ͷ఺͸ 1෺ମʹ͖ͭ 1ͭͷΈ • SSD ౳ͷΑ͏ʹ IoU ͷॏͳΓ۩߹Ͱ background ͔൱͔Λ෼͚ͳ͍ • ෳ਺ box ग़͞ͳ͍͜ͱΛલఏͱ͍ͯ͠Δ • ಉ͡ΫϥεͰॏͳͬͯ͠·͏৔߹͕͋Δ͕શମͷ 0.1 % ະຬͰ RCNN(2% ະ ຬ) ΑΓখ͍͞ 6
  4. 8.

    ͜Ε·ͰͷϞσϧͱͷҧ͍ • Object detec*on with implicit anchors(SSD, YOLO, Re*naNet ౳)ͱͷҧ͍

    • CenterNet͸ശͷॏͳΓͰ͸ͳ͘ҐஔͷΈʹج͍ͮͯʮΞϯΧʔʯΛׂ౰ • લܠͱഎܠͷ෼ྨʹؔ͢Δखಈͷ͖͍͠஋͸ͳ͍(IoU 0.5 > ͱ͔) • ෺ମຖʹϙδςΟϒͳΞϯΧʔ͸1͚ͭͩͳͷͰ NMS Λඞཁͱ͠ͳ͍ • We simply extract local peaks in the keypoint heatmap • keypoint heatmap ͔ΒϩʔΧϧϐʔΫΛநग़͢Δ͚ͩͰྑ͍ 8
  5. 9.

    ͜Ε·ͰͷϞσϧͱͷҧ͍ • Object detec*on with implicit anchors(SSD, YOLO, Re*naNet ౳)ͱͷҧ͍

    • CenterNet͸ΑΓେ͖ͳग़ྗղ૾౓Λ࢖͏ • mask r-cnn ͱ͔ͱൺֱͯ͠ • output stride of 16 • ͜ΕʹΑΓෳ਺ͷΞϯΧʔ͕ෆཁͱͳΔʁʁʁʁ • [1711.08189] An Analysis of Scale Invariance in Object Detec*on - SNIP 9
  6. 10.

    ͜Ε·ͰͷϞσϧͱͷҧ͍ • Object detec*on by keypoint es*ma*on(CornerNet, ExtremeNet ౳)ͱͷҧ͍ •

    ্ه 2ͭ͸ keypoint ݕग़ޙʹ ૊Έ߹ΘͤΛ grouping ͢Δඞཁ͕͋Δ • ஗͘ͳͬͯ͠·͏ • CenterNet ͸ඞཁͱ͠ͳ͍ • ଎͍ʂ 10
  7. 11.
  8. 13.

    ͦͷଞײ૝ • Backbone ͱͯ͠ DLA Λ࢖͑ΔͷΛॳΊͯ஌ͬͨ • Ή͠Ζ DLA ॳΊͯ஌Γ·ͨ͠

    ! • NMS ͕ෆཁʹͳΔͷ͸஍ຯʹخ͍͠ • anchor ͕ফ͑Δͷ΋خ͍͠ • খ͍͞෺ମʹରͯ͠ͲΕ͚ͩରԠͰ͖Δ͔֬ೝ͠ͳ͍ͱ 13