Coarse to Fine Multi-Resolution Temporal Convolutional Network

TL;DR

This paper introduces a coarse-to-fine multi-resolution temporal convolutional network with a novel encoder-decoder structure, multi-resolution augmentation, and an action loss, significantly improving temporal video segmentation accuracy and smoothness.

Contribution

It proposes a new multi-resolution encoder-decoder architecture with ensemble and augmentation strategies, eliminating the need for extra refinement modules in video segmentation.

Findings

Outperforms state-of-the-art on three benchmarks

Produces smoother, more accurate segmentations

Enhances robustness with multi-resolution training

Abstract

Temporal convolutional networks (TCNs) are a commonly used architecture for temporal video segmentation. TCNs however, tend to suffer from over-segmentation errors and require additional refinement modules to ensure smoothness and temporal coherency. In this work, we propose a novel temporal encoder-decoder to tackle the problem of sequence fragmentation. In particular, the decoder follows a coarse-to-fine structure with an implicit ensemble of multiple temporal resolutions. The ensembling produces smoother segmentations that are more accurate and better-calibrated, bypassing the need for additional refinement modules. In addition, we enhance our training with a multi-resolution feature-augmentation strategy to promote robustness to varying temporal resolutions. Finally, to support our architecture and encourage further sequence coherency, we propose an action loss that penalizes misclassifications at the video level. Experiments show that our stand-alone architecture, together with our novel feature-augmentation strategy and new loss, outperforms the state-of-the-art on three temporal video segmentation benchmarks.