Stella X. Yu : Papers / Google Scholar

Modeling Semantic Correlation and Hierarchy for Real-world Wildlife Recognition
Dong-Jin Kim and Zhongqi Miao and Yunhui Guo and Stella X. Yu and Kyle Landolt and Mark Koneff and Travis Harrison
Neural Information Processing Systems Workshop on Human in the Loop Learning, New Orleans, Louisiana, 2 December 2022
Paper | Poster

In wildlife imagery, the main challenges for a model to assist human annotation are two-fold: (1) the training dataset is usually imbalanced, which makes the model's suggestion biased, and (2) there are complex taxonomies in the classes. We establish a simple and efficient baseline, including the debiasing loss function and the hyperbolic network architecture, to address these issues and achieve noticeable improvements in image classification accuracy compared to a naive method. Moreover, we propose leveraging the semantic correlation to train the model more effectively by adding a co-occurrence layer to our model during training. The proposed semantic correlation-based learning method significantly improves the performance. We demonstrate the efficacy of our method in both our real-world wildlife areal survey recognition dataset and the public image classification dataset, CIFAR100-LT and CIFAR10-LT.

semantic correlation, visual hierarchy, wildlife recognition