Object proposals play a central role in determining detector accuracy. The original implementation of FastR-CNN with Selective Search proposals[32]has an AP of 19.3. Our MultiPath network improves this to 22.8 AP using these same proposals. Switching to DeepMask proposals [23, 24] increases accuracy by a further very substantial 5.1 points to 27.9 AP. Figure 3 shows AP50 and AP for varying number and type of proposals. Not only is accuracy substantially higher using DeepMask ,fewer proposals are necessary to achieve top performance. Our results saturate with around 400 DeepMask proposals per image and using just 50 DeepMask proposals matches accuracy with 2000 Selective Search proposals. Interestingly, our setup substantially reduces the benefits provided by bounding box regression. With the original Fast R-CNN and Selective Search proposals, box regression increases AP by 3.5 points, but with our MultiPath model and DeepMask proposals, box regression only increases AP by 1.1 points. See Table 2, left, for details.
Object proposals play a central role in determining detector accuracy. The original implementation of FastR-CNN with Selective Search proposals[32]has an AP of 19.3. Our MultiPath network improves this to 22.8 AP using these same proposals. Switching to DeepMask proposals [23, 24] increases accuracy by a further very substantial 5.1 points to 27.9 AP. Figure 3 shows AP50 and AP for varying number and type of proposals. Not only is accuracy substantially higher using DeepMask ,fewer proposals are necessary to achieve top performance. Our results saturate with around 400 DeepMask proposals per image and using just 50 DeepMask proposals matches accuracy with 2000 Selective Search proposals. Interestingly, our setup substantially reduces the benefits provided by bounding box regression. With the original Fast R-CNN and Selective Search proposals, box regression increases AP by 3.5 points, but with our MultiPath model and DeepMask proposals, box regression only increases AP by 1.1 points. See Table 2, left, for details.
การแปล กรุณารอสักครู่..
