Optimizing the trade-off between single-stage and two-stage deep object detectors using image difficulty prediction
P Soviany, RT Ionescu - 2018 20th International Symposium on …, 2018 - ieeexplore.ieee.org
There are mainly two types of state-of-the-art object detectors. On one hand, we have two-
stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or
Mask R-CNN, that (i) use a Region Proposal Network to generate regions of interests in the
first stage and (ii) send the region proposals down the pipeline for object classification and
bounding-box regression. Such models reach the highest accuracy rates, but are typically
slower. On the other hand, we have single-stage detectors, such as YOLO (You Only Look …
stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or
Mask R-CNN, that (i) use a Region Proposal Network to generate regions of interests in the
first stage and (ii) send the region proposals down the pipeline for object classification and
bounding-box regression. Such models reach the highest accuracy rates, but are typically
slower. On the other hand, we have single-stage detectors, such as YOLO (You Only Look …
Optimizing the trade-off between single-stage and two-stage object detectors using image difficulty prediction
P Soviany, RT Ionescu - arXiv preprint arXiv:1803.08707, 2018 - arxiv.org
There are mainly two types of state-of-the-art object detectors. On one hand, we have two-
stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or
Mask R-CNN, that (i) use a Region Proposal Network to generate regions of interests in the
first stage and (ii) send the region proposals down the pipeline for object classification and
bounding-box regression. Such models reach the highest accuracy rates, but are typically
slower. On the other hand, we have single-stage detectors, such as YOLO (You Only Look …
stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or
Mask R-CNN, that (i) use a Region Proposal Network to generate regions of interests in the
first stage and (ii) send the region proposals down the pipeline for object classification and
bounding-box regression. Such models reach the highest accuracy rates, but are typically
slower. On the other hand, we have single-stage detectors, such as YOLO (You Only Look …
