CVJul 24, 2022

Explored An Effective Methodology for Fine-Grained Snake Recognition

arXiv:2207.11637v11 citationsh-index: 12
Originality Incremental advance
AI Analysis

This work addresses a domain-specific problem in computer vision for fine-grained snake identification, with incremental improvements in methodology.

The paper tackled fine-grained snake recognition by proposing a multimodal backbone, new loss functions, and joint self-supervised and supervised training, achieving a macro F1 score of 92.7% on a private dataset and 89.4% on a public dataset, securing first place in the SnakeCLEF2022 competition.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes