One-Shot Modulation Network for Semi-supervised Video Segmentation
OSMN: One-Shot Modulation Network for Semi-supervised Video Segmentation
In this work, we propose to use a meta neural network named modulator to manipulate the intermediate layers of the segmentation network given the appearance of the object in the first frame. Our method only takes 140ms/frame for inference on DAVIS dataset.
Linjieyangsc_-video_seg-_model_structure.png
Abstruct
Video object segmentation targets at segmenting a specific object throughout a video sequence, given only an annotated first frame. Recent deep learning based approaches find it effective by fine-tuning a general-purpose segmentation model on the annotated frame using hundreds of iterations of gradient descent. Despite the high accuracy these methods achieve, the fine-tuning process is inefficient and fail to meet the requirements of real world applications. We propose a novel approach that uses a single forward pass to adapt the segmentation model to the appearance of a specific object. Specifically, a second meta neural network named modulator is learned to manipulate the intermediate layers of the segmentation network given limited visual and spatial information of the target object. The experiments show that our approach is 70times faster than fine-tuning approaches while achieving similar accuracy.
Documentation
- Efficient Video Object Segmentation via Network Modulation
- https://arxiv.org/abs/1802.01218
-
1802.01218.pdf