Classification for everyone : Building geography agnostic models for fairer recognition

We fine tune two popular image recognition models to In this paper, we analyze different methods to mitigate run our experiments - VGG [14] and ResNet [5], both pretrained inherent geographical biases present in state of the art image on ImageNet. First, we test out different techniques classification models. We first quantitatively present to tweak the fine tuning process - weighting the images by this bias in two datasets - The Dollar Street Dataset and income, under/over sampling the images to make the data ImageNet, using images with location information. We then distribution more uniform, and implementing a focal loss present different methods which can be employed to reduce [9] function to down-weight the inliers (easy examples) and this bias. Finally, we analyze the effectiveness of the different train on a sparse set of hard examples. We then try Adverserial techniques on making these models more robust to Discriminative Domain Adaptation (ADDA) [17] geographical locations of the images.