LVIS: A Dataset for Large Vocabulary Instance Segmentation
This dataset addresses the problem of instance segmentation with many categories for the computer vision research community, but it is incremental as it builds on existing datasets by expanding vocabulary and focusing on long-tail distributions.
The authors introduced LVIS, a dataset for large vocabulary instance segmentation, containing ~2 million masks for over 1000 categories in 164k images, which features a long tail of categories with few samples, posing a challenge for current deep learning methods.
Progress on object detection is enabled by datasets that focus the research community's attention on open challenges. This process led us from simple images to complex scenes and from bounding boxes to segmentation masks. In this work, we introduce LVIS (pronounced `el-vis'): a new dataset for Large Vocabulary Instance Segmentation. We plan to collect ~2 million high-quality instance segmentation masks for over 1000 entry-level object categories in 164k images. Due to the Zipfian distribution of categories in natural images, LVIS naturally has a long tail of categories with few training samples. Given that state-of-the-art deep learning methods for object detection perform poorly in the low-sample regime, we believe that our dataset poses an important and exciting new scientific challenge. LVIS is available at http://www.lvisdataset.org.