论文标题
具有特权合并的细颗粒物种识别：通过监督注意力更好的样本效率
Fine-grained Species Recognition with Privileged Pooling: Better Sample Efficiency Through Supervised Attention
论文作者
论文摘要
我们提出了一个用于监督图像分类的方案，该方案以培训数据的关键点注释的形式使用特权信息，以从小型和/或有偏见的培训集中学习强模型。我们的主要动机是对动物物种的认可，例如生物多样性建模，这是由于稀有物种而导致的长尾物种分布以及强大的数据集偏见，例如相机陷阱中的重复场景背景，这是具有挑战性的。为了应对这些挑战，我们提出了一种视觉注意机制，该机制是通过关键点注释来监督的，该注释突出了重要的对象部分。这种特权信息仅在培训期间才能实现为一种新颖的特权合并操作，并有助于模型专注于歧视性的区域。在使用三个不同动物物种数据集的实验中，我们表明具有特权合并的深网可以更有效地使用小型训练集并更好地概括。
We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from small and/or biased training sets. Our main motivation is the recognition of animal species for ecological applications such as biodiversity modelling, which is challenging because of long-tailed species distributions due to rare species, and strong dataset biases such as repetitive scene background in camera traps. To counteract these challenges, we propose a visual attention mechanism that is supervised via keypoint annotations that highlight important object parts. This privileged information, implemented as a novel privileged pooling operation, is only required during training and helps the model to focus on regions that are discriminative. In experiments with three different animal species datasets, we show that deep networks with privileged pooling can use small training sets more efficiently and generalize better.
