Frame-To-Frame Consistent Semantic Segmentation

TL;DR

This paper introduces a method for achieving temporally consistent semantic segmentation in videos by using ConvLSTM to propagate features across frames and penalizing inconsistencies, resulting in improved accuracy and stability over single-frame methods.

Contribution

The paper presents a novel CNN architecture with ConvLSTM for temporal feature propagation and a loss function to enforce consistency, enhancing video segmentation performance.

Findings

mIoU increased from 45.2% to 57.9% with video data

Inconsistency reduced from 4.5% to 1.3%

Temporal information improves segmentation accuracy and consistency

Abstract

In this work, we aim for temporally consistent semantic segmentation throughout frames in a video. Many semantic segmentation algorithms process images individually which leads to an inconsistent scene interpretation due to illumination changes, occlusions and other variations over time. To achieve a temporally consistent prediction, we train a convolutional neural network (CNN) which propagates features through consecutive frames in a video using a convolutional long short term memory (ConvLSTM) cell. Besides the temporal feature propagation, we penalize inconsistencies in our loss function. We show in our experiments that the performance improves when utilizing video information compared to single frame prediction. The mean intersection over union (mIoU) metric on the Cityscapes validation set increases from 45.2 % for the single frames to 57.9 % for video data after implementing the ConvLSTM to propagate features trough time on the ESPNet. Most importantly, inconsistency decreases from 4.5 % to 1.3 % which is a reduction by 71.1 %. Our results indicate that the added temporal information produces a frame-to-frame consistent and more accurate image understanding compared to single frame processing. Code and videos are available at https://github.com/mrebol/f2f-consistent-semantic-segmentation