IEEE Trans Pattern Anal Mach Intell. 2016 Apr;38(4):666-76. doi: 10.1109/TPAMI.2015.2439285.
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 a 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 "BubbleBank" representation that uses the human selected bubbles to improve machine recognition performance. Finally, we demonstrate how to extend BubbleBank to a view-invariant 3D representation. Experiments demonstrate that our approach yields large improvements over the previous state of the art on challenging benchmarks.
细粒度识别关注的是次级别分类，其中对象类别的区分是高度局部的。与基本水平识别相比，细粒度分类可能更具挑战性，因为通常数据较少，鉴别特征较少。这需要使用更强的先验知识进行特征选择。在这项工作中，我们将人类纳入循环，以帮助计算机选择鉴别特征。我们引入了一种名为“Bubbles”的新在线游戏，该游戏揭示了人类使用的鉴别特征。玩家的目标是识别一个严重模糊的图像的类别。在游戏中，玩家可以选择揭示圆形区域（“气泡”）的全部细节，但会受到一定的惩罚。通过适当的设置，游戏会生成具有一定质量保证的鉴别气泡。接下来，我们提出了“BubbleBank”表示方法，该方法使用人类选择的气泡来提高机器识别性能。最后，我们演示了如何将 BubbleBank 扩展到视图不变的 3D 表示。实验表明，我们的方法在具有挑战性的基准上显著优于以前的最新技术。
