论文标题
解决零射门学习问题的自我监督方法
Self-Supervised Approach to Addressing Zero-Shot Learning Problem
论文作者
论文摘要
近年来，在涉及计算机视觉和自然语言处理的应用中，自我监管的学习取得了巨大的成功。借口任务的类型对于这一提高性能很重要。一个常见的借口任务是衡量图像对之间的相似性和差异。在这种情况下，构成负面对的两个图像与人类明显不同。但是，在昆虫学中，物种几乎是无法区分的，因此很难区分。在这项研究中，我们通过学习将嵌入式嵌入的大黄蜂物种对的嵌入方式来探索了暹罗神经网络的性能，这些损失是不同的，并将类似的嵌入在一起。我们的实验结果表明，零射击实例的F1得分为61％，这一表现显示出与训练集共享相交的类样品的11％改善。
In recent years, self-supervised learning has had significant success in applications involving computer vision and natural language processing. The type of pretext task is important to this boost in performance. One common pretext task is the measure of similarity and dissimilarity between pairs of images. In this scenario, the two images that make up the negative pair are visibly different to humans. However, in entomology, species are nearly indistinguishable and thus hard to differentiate. In this study, we explored the performance of a Siamese neural network using contrastive loss by learning to push apart embeddings of bumblebee species pair that are dissimilar, and pull together similar embeddings. Our experimental results show a 61% F1-score on zero-shot instances, a performance showing 11% improvement on samples of classes that share intersections with the training set.
