# Tamed Warping Network for High-Resolution Semantic Video Segmentation

Source: [Tamed Warping Network for High-Resolution Semantic Video Segmentation](<https://www.sota2.com/research/paper/68fa6ffd1e209131cea485f8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:31:17.072Z

Authors: Songyuan Li, Junyi Feng, Xi Li

Published: 2020-05-04T09:36:03.000Z

## Abstract

Recent approaches for fast semantic video segmentation have reduced redundancy by warping feature maps across adjacent frames, greatly speeding up the inference phase. However, the accuracy drops seriously owing to the errors incurred by warping. In this paper, we propose a novel framework and design a simple and effective correction stage after warping. Specifically, we build a non-key-frame CNN, fusing warped context features with current spatial details. Based on the feature fusion, our Context Feature Rectification~(CFR) module learns the model's difference from a per-frame model to correct the warped features. Furthermore, our Residual-Guided Attention~(RGA) module utilizes the residual maps in the compressed domain to help CRF focus on error-prone regions. Results on Cityscapes show that the accuracy significantly increases from $67.3\\%$ to $71.6\\%$, and the speed edges down from $65.5$ FPS to $61.8$ FPS at a resolution of $1024\\times 2048$. For non-rigid categories, e.g., \`\`human'' and \`\`object'', the improvements are even higher than 18 percentage points.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2005.01344>)

[PDF](<https://arxiv.org/pdf/2005.01344.pdf>)
