Instance Embedding Transfer to Unsupervised Video Object Segmentation
arXiv:1801.00908
Abstract
We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables identifying all pixels belonging to the same object. Though trained on static images, the instance embeddings are stable over consecutive video frames, which allows us to link objects together over time. Thus, we adapt the instance networks trained on static images to video object segmentation and incorporate the embeddings with objectness and optical flow features, without model retraining or online fine-tuning. The proposed method outperforms state-of-the-art unsupervised segmentation methods in the DAVIS dataset and the FBMS dataset.
arXiv commentTo appear in CVPR 2018
References in corpus (13)
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Deep Residual Learning for Image Recognition
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Fully Convolutional Networks for Semantic Segmentation
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Semantic Instance Segmentation with a Discriminative Loss Function
- SfM-Net: Learning of Structure and Motion from Video
- Semantic Instance Segmentation via Deep Metric Learning
- FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos
- Learning Video Object Segmentation from Static Images
- Learning Video Object Segmentation with Visual Memory
- Video Propagation Networks
- Semantic Segmentation with Reverse Attention
Cited by in corpus (5)
- ALBA : Reinforcement Learning for Video Object Segmentation
- A Transductive Approach for Video Object Segmentation
- See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
- Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
- Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation