Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Reading Circle (Weakly-Supervised Semantic Segmentation via Sub-category Exploration)

pyman
July 01, 2020

Reading Circle (Weakly-Supervised Semantic Segmentation via Sub-category Exploration)

Explanation of Weakly-Supervised Semantic Segmentation
via Sub-category Exploration [Chang+, CVPR20]

pyman

July 01, 2020
Tweet

More Decks by pyman

Other Decks in Research

Transcript

  1. Semantic Segmentation Assign a semantic category to each pixel. 2

    Supervised Dataset : image & pixel-level class label ✗ huge annotation cost ↓ Weakly-supervised Dataset : image & image-level class label
  2. Weakly-Supervised SS Methods Three steps to train on the image-level

    label. 1. predict an initial category-wise response map to localize the object 2. refine the initial response as the pseudo GT 3. train the segmentation network based on pseudo labels 3 1 2 3
  3. Weakly-Supervised SS Methods Three steps to train on the image-level

    label. 1. predict an initial category-wise response map to localize the object 2. refine the initial response as the pseudo GT 3. train the segmentation network based on pseudo labels 4 AffinityNet [Ahn+, CVPR18] CRF [Krahenbuhl+, NeurIPS11] 1 2 3
  4. Weakly-Supervised SS Methods Three steps to train on the image-level

    label. 1. predict an initial category-wise response map to localize the object 2. refine the initial response as the pseudo GT 3. train the segmentation network based on pseudo labels 9 Deeplab-v2 [Chen+, CoRR16] 1 2 3
  5. Weakly-Supervised SS Methods Three steps to train on the image-level

    label. 1. predict an initial category-wise response map to localize the object 2. refine the initial response as the pseudo GT 3. train the segmentation network based on pseudo labels 10 1
  6. Method Introduce sub-category exploration. 18 jointly optimize parent classifier and

    sub-category classifier → multi-label classification loss
  7. Dataset PASCAL VOC 2012 semantic segmentation benchmark 21 categories one

    or multiple object class 10,528 images in training set 1,449 images in validation set 1,456 images in test set 20
  8. Conclusion Weakly-supervised Learning 1. generate pseudo GT label 2. apply

    supervised learning Weakly-supervised Semantic Segmentation sub-category exploration ↓ widely covered CAM ↓ better pseudo GT label 29