Table 5 Comparison of mAPs on Cars-196 under FGIR.

From: Learning optimal image representations through noise injection for fine-grained search

Method

LBP

HOG

ResNet18 (Pretrained)

Kumar et al.29

Our method

mAP

0.011

0.013

0.045

0.765

0.802

  1. Significant values are in [bold].
Back to article page