The following paper investigates the effectiveness of incorporating human salience into the task of calorie prediction from images of food. We observe a 32.2% relative improvement when incorporating saliency maps on the images of food highlighting the most calorie regions. We also attempt to further improve the accuracy by starting the best models using pre-trained weights on similar tasks of mass estimation and food classification. However, we observe no improvement. Surprisingly, we also find that our best model was not able to surpass the original performance published alongside the test dataset, Nutrition5k. We use ResNet50 and Xception as the base models for our experiment.
View on arXiv