Occlusion Robust Part-aware Object Classification through Part Attention and Redundant Features Suppression
TimeThursday, December 1610am - 6pm JST
LocationHall E (B2F, E Block)
DescriptionWe propose a part-aware deep learning approach for partial occlusion robust object classification.
We train a network without occluded objects in training time and test the network under partial occlusions.