论文标题
探索了一种有效的细粒蛇识别方法
Explored An Effective Methodology for Fine-Grained Snake Recognition
论文作者
论文摘要
细粒度的视觉分类（FGVC）是计算机视觉和模式识别的一个长期存在的基本问题，并为一系列现实世界的应用程序提供了基础。本文用FGVC描述了我们在Snakeclef2022上的贡献。首先，我们设计了一个强大的多模式主链，以利用各种元信息来帮助细粒度识别。其次，我们提供了新的损失功能，可以用数据集解决长时间的分布。然后，为了充分利用未标记的数据集，我们使用自我监督的学习和监督学习联合培训来提供预训练的模型。此外，我们的实验也考虑了一些有效的数据过程技巧。最后但并非最不重要的一点是，在下游任务中进行了微调，艰苦的采矿，固定的模型性能。广泛的实验表明，我们的方法可以有效地提高细粒识别的性能。我们的方法分别可以在私人和公共数据集上获得宏F1分别为92.7％和89.4％，这是私人排行榜上参与者的第一名。
Fine-Grained Visual Classification (FGVC) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. This paper describes our contribution at SnakeCLEF2022 with FGVC. Firstly, we design a strong multimodal backbone to utilize various meta-information to assist in fine-grained identification. Secondly, we provide new loss functions to solve the long tail distribution with dataset. Then, in order to take full advantage of unlabeled datasets, we use self-supervised learning and supervised learning joint training to provide pre-trained model. Moreover, some effective data process tricks also are considered in our experiments. Last but not least, fine-tuned in downstream task with hard mining, ensambled kinds of model performance. Extensive experiments demonstrate that our method can effectively improve the performance of fine-grained recognition. Our method can achieve a macro f1 score 92.7% and 89.4% on private and public dataset, respectively, which is the 1st place among the participators on private leaderboard.
