Please enable JavaScript.

Coggle requires JavaScript to display documents.

Focal Loss (Loss function (factor (1 − pt)γ, standard cross entropy…

- - - - Mask R-CNN
      - Faster R-CNN
  - - - why?
        
        extreme foreground-background class imbalance encountered
        during training of dense detectors is the central cause
    - - YOLO
      - SSD
      - promising results, yielding faster detectors with accuracy within 10-40% relative to state-of-the-art two-stage method
      - This paper pushes the envelop further
        
        present a onestage object detector that, for the first time, matches the state-of-the-art COCO AP of more complex two-stage detectors, such as the Feature Pyramid Network (FPN) or Mask R-CNN variants of Faster R-CNN
        
        To achieve this result, we identify class imbalance during training as the main obstacle impeding one-stage detector from achieving state-of-the-art accuracy and propose a new loss function that eliminates this barrier
  - - - this
        two-stage framework consistently achieves top accuracy on
        the challenging COCO benchmark
- - - - DeepMask
      - RPN
      - .... rapidly narrows down the number of candidate object locations to a small number (e.g., 1-2k), filtering out most background samples
      - Selective Search
      - EdgeBoxes
    - - sampling heuristics
        
        fixed foreground-to-background ratio (1:3)
        
        online hard example mining (OHEM)
        
        are performed to maintain a manageable balance between foreground and background