vix.ing · top · new · best · stats

LVIS: A Dataset for Large Vocabulary Instance Segmentation

2019/08/08 by Agrim Gupta, Piotr Dollár, Gupta, Agrim +3 · 164 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Multimodal Machine Learning Applications #cs.CV

paper · pdf · doi:10.48550/arxiv.1908.03195

Extension of the CVPR'19 paper describing release v0.5, the LVIS Challenge, and baseline results

arxiv created 2019/09/15 · arxiv updated 2019/09/17

Abstract

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.

Citations

Cited by

Related