Transcription of Focal Loss for Dense Object Detection
{{id}} {{{paragraph}}}
Example: barber
Focal Loss for Dense Object Detection
Focal Loss for Dense Object DetectionTsung-Yi LinPriya GoyalRoss GirshickKaiming HePiotr Doll arFacebook AI Research (FAIR) of ground truth class012345loss = 0 = = 1 = 2 = 5well-classi edexampleswell-classi edexamplesCE(pt) = log(pt)FL(pt) = (1 pt) log(pt)Figure 1. We propose a novel loss we term theFocal Lossthatadds a factor(1 pt) to the standard cross entropy >0reduces the relative loss for well-classified examples(pt> .5), putting more focus on hard, misclassified examples. Asour experiments will demonstrate, the proposed Focal loss enablestraining highly accurate Dense Object detectors in the presence ofvast numbers of easy background highest accuracy Object detectors to date are basedon a two-stage approach popularized by R-CNN, where aclassifier is applied to asparseset of candidate Object lo-cations.
and the number of proposals, but one-stage methods trailed in accuracy even with a larger compute budget [17]. In con-trast, the aim of this work is to understand if one-stage de-tectors can match or surpass the accuracy of two-stage de-tectors while running at similar or faster speeds. The design of our RetinaNet detector shares many simi-
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: