The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation
Sergi Caelles, Jordi Pont-Tuset, Federico Perazzi, Alberto Montes, Kevis-Kokitsi Maninis, Luc Van Gool S. Caelles, K.-K. Maninis, and L. Van Gool are with the Computer Vision Laboratory, ETH Zürich, Switzerland. J. Pont-Tuset and A. Montes are with Google AI. F. Perazzi is with Adobe Research. Contacts and updated information can be found in the challenge website: http://davischallenge.org
Abstract
We present the 2019 DAVIS Challenge on Video Object Segmentation, the third edition of the DAVIS Challenge series, a public competition designed for the task of Video Object Segmentation (VOS). In addition to the original semi-supervised track and the interactive track introduced in the previous edition [1], a new unsupervised multi-object track will be featured this year. In the newly introduced track, participants are asked to provide non-overlapping object proposals on each image, along with an identifier linking them between frames (i.e. video object proposals), without any test-time human supervision (no scribbles or masks provided on the test video). In order to do so, we have re-annotated the train and val sets of DAVIS 2017 [2] in a concise way that facilitates the unsupervised track, and created new test-dev and test-challenge sets for the competition. Definitions, rules, and evaluation metrics for the unsupervised track are described in detail in this paper.
中文速览
视频目标分割（Video Object Segmentation）领域长期缺少一个标准化的"无监督多目标"评测平台——已有方法要么只处理单目标，要么依赖测试时的人工标注输入。为此，2019年DAVIS挑战赛在原有半监督和交互式两个赛道之上，新增了无监督多目标视频目标分割赛道：参赛方法须在完全不依赖任何测试时人工输入的条件下，自动给出每帧中互不重叠的目标提案，并在帧间保持目标身份一致。组织者依据"人眼注意力"准则对DAVIS 2017的训练集和验证集重新标注，使语义更一致，同时新增60条测试序列，并采用匈牙利算法对预测提案与真值目标做最优二分图匹配，以J&F指标衡量性能。基线方法RVOS在该赛道上表现明显低于半监督场景，说明无监督多目标分割仍极具挑战性，该赛道的设立将有力推动全自动视频分析技术的发展。
原文 arXiv:1905.00737;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1905.00737v1