Transcription of Rich Feature Hierarchies for Accurate Object Detection and ...
{{id}} {{{paragraph}}}
Example: barber
Rich Feature Hierarchies for Accurate Object Detection and ...
Rich Feature Hierarchies for Accurate Object Detection and semantic segmentationRoss Girshick1 Jeff Donahue1,2 Trevor Darrell1,2 Jitendra Malik11UC Berkeley Detection performance, as measured on thecanonical PASCAL VOC dataset, has plateaued in the lastfew years. The best-performing methods are complex en-semble systems that typically combine multiple low-levelimage features with high-level context. In this paper, wepropose a simple and scalable Detection algorithm that im-proves mean average precision (mAP) by more than 30%relative to the previous best result on VOC 2012 achievinga mAP of Our approach combines two key insights:(1) one can apply high-capacity convolutional neural net-works (CNNs) to bottom-up region proposals in order tolocalize and segment objects and (2) when labeled trainingdata is scarce, supervised pre-training for an auxiliary task,followed by domain-specific fine-tuning, yields a signifi-cant
Feature extraction. We extract a 4096-dimensional fea-ture vector from each region proposal using the Caffe [21] implementation of the CNN described by Krizhevsky et al. [22]. Features are computed by forward propagating a mean-subtracted 227 227 RGB image through five con-volutional layers and two fully connected layers. We refer
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: