A Benchmark of Long-tailed Instance Segmentation with Noisy Labels
This work addresses a practical challenge in computer vision for real-world applications where datasets are long-tailed and noisy, but it is incremental as it primarily benchmarks existing methods.
The authors tackled instance segmentation on a long-tailed dataset with noisy labels by creating a new dataset and evaluating existing algorithms, finding that noise hampers learning of rare categories and reduces overall performance, with specific metrics like decreased mAP scores reported.
In this paper, we consider the instance segmentation task on a long-tailed dataset, which contains label noise, i.e., some of the annotations are incorrect. There are two main reasons making this case realistic. First, datasets collected from real world usually obey a long-tailed distribution. Second, for instance segmentation datasets, as there are many instances in one image and some of them are tiny, it is easier to introduce noise into the annotations. Specifically, we propose a new dataset, which is a large vocabulary long-tailed dataset containing label noise for instance segmentation. Furthermore, we evaluate previous proposed instance segmentation algorithms on this dataset. The results indicate that the noise in the training dataset will hamper the model in learning rare categories and decrease the overall performance, and inspire us to explore more effective approaches to address this practical challenge. The code and dataset are available in https://github.com/GuanlinLee/Noisy-LVIS.