FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation

Recently, there has been a lot of progress for video object segmentation (VOS). However, many of the most successful methods are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use. In this work, we propose FEELVOS as a simple and fast method which does not rely on fine-tuning. In order to segment a video frame, FEELVOS uses a semantic pixel-wise embedding together with a global and a local matching mechanism to transfer information from the first frame and from the previous frame of the video to the current frame. In contrast to previous work, our embedding is only used as an internal guidance of a convolutional network. Our novel dynamic segmentation head allows us to train the network including the embedding end-to-end for the multiple object segmentation task. We achieve a new state of the art in video object segmentation without fine-tuning on the DAVIS 2017 validation set with a J&F measure of 69.0%.