Fine-Grained Crowdsourcing for Fine-Grained Recognition

Jia Deng, Jonathan Krause, Li Fei-Fei
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
Fine-grained recognition concerns categorization at sub-ordinate levels, where the distinction between object classes is highly local. Compared to basic level recognition, fine-grained categorization can be more challenging as there are in general less data and fewer discriminative features. This necessitates the use of stronger prior for feature selection. In this work, we include humans in the loop to help computers select discriminative features. We introduce a novel online game called
more » ... es" that reveals discriminative features humans use. The player's goal is to identify the category of a heavily blurred image. During the game, the player can choose to reveal full details of circular regions ("bubbles"), with a certain penalty. With proper setup the game generates discriminative bubbles with assured quality. We next propose the "BubbleBank" algorithm that uses the human selected bubbles to improve machine recognition performance. Experiments demonstrate that our approach yields large improvements over the previous state of the art on challenging benchmarks.
doi:10.1109/cvpr.2013.81 dblp:conf/cvpr/DengK013 fatcat:4n4brjjy7fb3pbufe7apode4ea