Fine-Grained Crowdsourcing for Fine-Grained 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 "Bubbles" 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 "Bubble Bank" 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

Extracted Key Phrases

11 Figures and Tables

Citations per Year

193 Citations

Semantic Scholar estimates that this publication has 193 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Deng2013FineGrainedCF, title={Fine-Grained Crowdsourcing for Fine-Grained Recognition}, author={Jia Deng and Jonathan Krause and Fei-fei Li}, journal={2013 IEEE Conference on Computer Vision and Pattern Recognition}, year={2013}, pages={580-587} }