论文标题
部分可观测时空混沌系统的无模型预测
Recognition of Unseen Bird Species by Learning from Field Guides
论文作者
论文摘要
我们利用野外指南学习鸟类识别，特别是对看不见的物种的零拍识别。现场指南中包含的插图故意关注每个物种的判别特性，并且可以作为旁边信息，以将知识从可见的鸟类转移到看不见的鸟类。我们研究了两种方法：（1）插图的对比编码，可以将其馈入标准的零照片学习方案； （2）一种新的方法，它利用了插图也是图像，并且在结构上比其他类型的侧面信息更相似。我们的研究结果表明，现场指南的插图很容易适用于广泛的物种，确实是零射击学习的侧面信息的竞争来源。在inaturalist2021数据集的子集中，有749个观察和739种，我们获得了$ 12 \％$ @top-1和$ 38 \％$ @top-10的分类准确性，这表明了田野指南的潜力，这些潜力与许多物种有关。我们的代码可从https://github.com/ac-rodriguez/zsl_billow获得
We exploit field guides to learn bird species recognition, in particular zero-shot recognition of unseen species. Illustrations contained in field guides deliberately focus on discriminative properties of each species, and can serve as side information to transfer knowledge from seen to unseen bird species. We study two approaches: (1) a contrastive encoding of illustrations, which can be fed into standard zero-shot learning schemes; and (2) a novel method that leverages the fact that illustrations are also images and as such structurally more similar to photographs than other kinds of side information. Our results show that illustrations from field guides, which are readily available for a wide range of species, are indeed a competitive source of side information for zero-shot learning. On a subset of the iNaturalist2021 dataset with 749 seen and 739 unseen species, we obtain a classification accuracy of unseen bird species of $12\%$ @top-1 and $38\%$ @top-10, which shows the potential of field guides for challenging real-world scenarios with many species. Our code is available at https://github.com/ac-rodriguez/zsl_billow
