Archives for focal loss
In the conventional object detectors, say, R-CNN, initially a set of object locations are generated and then these locations are classified whether they belong to the foreground or background classes using a CNN. This is working of a two-stage detector. In the case of one stage detectors like SSD, the accuracy is more when applied…
The post How RetinaNet Fixes The Shortcomings Of SSD With Focal Loss appeared first on Analytics India Magazine.
In the conventional object detectors, say, R-CNN, initially a set of object locations are generated and then these locations are classified whether they belong to the foreground or background classes using a CNN. This is working of a two-stage detector. In the case of one stage detectors like SSD, the accuracy is more when applied…
The post How RetinaNet Fixes The Shortcomings Of SSD With Focal Loss appeared first on Analytics India Magazine.