# Temporally Distributed Networks for Fast Video Semantic Segmentation

arXiv: https://arxiv.org/abs/2004.01800 · HTML: https://mlsanity.com/paper/2004.01800/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 30 of 77)

- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers](https://mlsanity.com/paper/2206.02066/) (2022)
- [Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation](https://mlsanity.com/paper/2204.04656/) (2022)
- [Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions](https://mlsanity.com/paper/2106.05022/) (2021)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [Temporal Memory Attention for Video Semantic Segmentation](https://mlsanity.com/paper/2102.08643/) (2021)
- [Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation](https://mlsanity.com/paper/2106.11958/) (2021)
- [Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations](https://mlsanity.com/paper/2308.11796/) (2023)
- [Skip-Convolutions for Efficient Video Processing](https://mlsanity.com/paper/2104.11487/) (2021)
- [AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation](https://mlsanity.com/paper/2110.12369/) (2021)
- [Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention](https://mlsanity.com/paper/2401.06312/) (2024)
- [Mask Propagation for Efficient Video Semantic Segmentation](https://mlsanity.com/paper/2310.18954/) (2023)
- [Local Memory Attention for Fast Video Semantic Segmentation](https://mlsanity.com/paper/2101.01715/) (2021)
- [Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation](https://mlsanity.com/paper/2207.10436/) (2022)
- [Learning Local and Global Temporal Contexts for Video Semantic Segmentation](https://mlsanity.com/paper/2204.03330/) (2022)
- [Domain Adaptive Video Segmentation via Temporal Consistency Regularization](https://mlsanity.com/paper/2107.11004/) (2021)
- [QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition](https://mlsanity.com/paper/2310.00132/) (2023)
- [MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds](https://mlsanity.com/paper/2307.09316/) (2023)
- [AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation](https://mlsanity.com/paper/2309.14065/) (2023)
- [Exploiting Temporal State Space Sharing for Video Semantic Segmentation](https://mlsanity.com/paper/2503.20824/) (2025)
- [Event-guided Low-light Video Semantic Segmentation](https://mlsanity.com/paper/2411.00639/) (2024)
- [Perceptual Consistency in Video Segmentation](https://mlsanity.com/paper/2110.12385/) (2021)
- [Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes](https://mlsanity.com/paper/2401.15261/) (2024)
- [GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video](https://mlsanity.com/paper/2103.08834/) (2021)
- [Rethinking Dilated Convolution for Real-time Semantic Segmentation](https://mlsanity.com/paper/2111.09957/) (2021)
- [RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation](https://mlsanity.com/paper/2203.04187/) (2022)
- [Domain Adaptive Video Segmentation via Temporal Pseudo Supervision](https://mlsanity.com/paper/2207.02372/) (2022)
- [Efficient Global-Local Memory for Real-time Instrument Segmentation of Robotic Surgical Video](https://mlsanity.com/paper/2109.13593/) (2021)

## Abstract (arXiv)

We present TDNet, a temporally distributed network designed for fast and accurate video semantic segmentation. We observe that features extracted from a certain high-level layer of a deep CNN can be approximated by composing features extracted from several shallower sub-networks. Leveraging the inherent temporal continuity in videos, we distribute these sub-networks over sequential frames. Therefore, at each time step, we only need to perform a lightweight computation to extract a sub-features group from a single sub-network. The full features used for segmentation are then recomposed by application of a novel attention propagation module that compensates for geometry deformation between frames. A grouped knowledge distillation loss is also introduced to further improve the representation power at both full and sub-feature levels. Experiments on Cityscapes, CamVid, and NYUD-v2 demonstrate that our method achieves state-of-the-art accuracy with significantly faster speed and lower latency.