Semantic Video Segmentation by Gated Recurrent Flow Propagation

By David Nilsson, Cristian Sminchisescu. 2016

243 citations recorded by the source corpus.

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 for video segmentation that is capable of leveraging the information present in unlabeled data, besides sparsely labeled frames, in order to improve semantic estimates. Our model combines a convolutional architecture and a spatiotemporal transformer recurrent layer that is 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 experiments in the challenging CityScapes and Camvid datasets, and for 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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring (2019, methodology): “While dealing with video data, additional temporal information can also be used to conduct spatiotemporal analysis [35–37] for segmentation.”
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation (2020, methodology): “Human-annotated ground-truth labels of certain frames in a video sequence could be propagated to other unlabeled frames via patch matching [4,6] or optical flow [54,23,94,53,56].”
Improving Semantic Segmentation via Video Propagation and Label Relaxation (2018, background): “Label propagation There are two main approaches to propagating labels: patch matching [2, 9] and optical flow [31, 16, 33].”
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (2019, unknown): “Still, the efficient test-time inference has led to their widespread adoption as a sub-module in applications requiring to process tempo ral information, including video object segmentation [13], video recognition [15, 43, 64], and video style transfer [11].”
Video Panoptic Segmentation (2020, unknown): “Despite the absence of a dataset for Video Semantic Segmentation (VSS), several approaches have been proposed in the literature [14, 21, 26, 33, 43].”
Survey on semantic segmentation using deep learning techniques (2019, background): “Nilsson et al. [151] present Gated Recurrent Flow Propagation network.”
A Survey on Deep Learning Technique for Video Segmentation (2021, background): “2018 GRFP [216] CVPRSemantic FCN + GRU ✓ Temporal Feature Aggregation Cityscapes [206]/CamVid [208]”
Predicting Deeper into the Future of Semantic Segmentation (2017, unknown): “In our work, we build upon the recent progress in this area [10, 25, 5, 46, 31, 30, 24], and develop models to predict the semantic segmentation of future video frames, given several preceding frames.”
Semantic Flow for Fast and Accurate Scene Parsing (2020, unknown): “[37] warps ﬁnal semantic maps.”