Semantic Video Segmentation by Gated Recurrent Flow Propagation
arXiv:1612.08871
Abstract
Semantic video segmentation is challenging due to the sheer amount of data that needs to be processed and labeled in order to construct accurate models. In this paper we present a deep, end-to-end trainable methodology to video segmentation that is capable of leveraging information present in unlabeled data in order to improve semantic estimates. Our model combines a convolutional architecture and a spatio-temporal transformer recurrent layer that are able to temporally propagate labeling information by means of optical flow, adaptively gated based on its locally estimated uncertainty. The flow, the recognition and the gated temporal propagation modules can be trained jointly, end-to-end. The temporal, gated recurrent flow propagation component of our model can be plugged into any static semantic segmentation architecture and turn it into a weakly supervised video processing one. Our extensive experiments in the challenging CityScapes and Camvid datasets, and based on multiple deep architectures, indicate that the resulting model can leverage unlabeled temporal frames, next to a labeled one, in order to improve both the video segmentation accuracy and the consistency of its temporal labeling, at no additional annotation cost and with little extra computation.
The experiments section is extended compared to the previous version
References in corpus (8)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Semantic Image Segmentation via Deep Parsing Network
- Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
- VideoLSTM Convolves, Attends and Flows for Action Recognition
- WarpNet: Weakly Supervised Matching for Single-view Reconstruction