کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
407422 | 678140 | 2016 | 8 صفحه PDF | دانلود رایگان |
Naive Bayes Nearest Neighbor classifier, despite its simplicity, has recently gained remarkable success in image classification. Inspired from such results, we originally introduce to model the discriminativity of features using the density estimation approach presented in NBNN. Features are then grouped into positive and negative ones according to their log-discriminativity. More importantly, we speculate that updating the detector using merely positive features works much more confidently than the one using both negative and positive features, and further validate it on the PASCAL VOC 2007 dataset and LabelMe dataset. Therefore, we propose to localize the object of interest using positive features. However, unlike traditional detectors in this field, scores of the proposed one always increase as the test region becomes larger. To address this issue, we utilize context features to estimate scales of the objects and their probabilities, and then combine these estimations with the proposed detector to localize the target objects. We finally demonstrate the effectiveness of the proposed approach on PASCAL VOC 2007 in detail, due to its standard configurations on the training and test sets.
Journal: Neurocomputing - Volume 171, 1 January 2016, Pages 463–470