# Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video

arXiv: https://arxiv.org/abs/1807.06667 · HTML: https://mlsanity.com/paper/1807.06667/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2018.

## Built on by (most cited first, 30 of 78)

- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [Semantic Segmentation using Vision Transformers: A survey](https://mlsanity.com/paper/2305.03273/) (2023)
- [TubeFormer-DeepLab: Video Mask Transformer](https://mlsanity.com/paper/2205.15361/) (2022)
- [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)
- [LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment](https://mlsanity.com/paper/2103.02263/) (2021)
- [Mask Propagation for Efficient Video Semantic Segmentation](https://mlsanity.com/paper/2310.18954/) (2023)
- [Learning to Associate Every Segment for Video Panoptic Segmentation](https://mlsanity.com/paper/2106.09453/) (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)
- [Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation](https://mlsanity.com/paper/2304.04694/) (2023)
- [Domain Adaptive Video Segmentation via Temporal Consistency Regularization](https://mlsanity.com/paper/2107.11004/) (2021)
- [DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos](https://mlsanity.com/paper/2203.03996/) (2022)
- [A spatio-temporal network for video semantic segmentation in surgical videos](https://mlsanity.com/paper/2306.11052/) (2023)
- [Exploiting Temporal State Space Sharing for Video Semantic Segmentation](https://mlsanity.com/paper/2503.20824/) (2025)
- [Biomedical SAM 2: Segment Anything in Biomedical Images and Videos](https://mlsanity.com/paper/2408.03286/) (2024)
- [Event-guided Low-light Video Semantic Segmentation](https://mlsanity.com/paper/2411.00639/) (2024)
- [Zero-Shot Scene Change Detection](https://mlsanity.com/paper/2406.11210/) (2024)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [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)
- [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)
- [Accelerating Video Object Segmentation with Compressed Video](https://mlsanity.com/paper/2107.12192/) (2021)
- [Delta Distillation for Efficient Video Processing](https://mlsanity.com/paper/2203.09594/) (2022)
- [MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation](https://mlsanity.com/paper/2209.04471/) (2022)
- [Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation](https://mlsanity.com/paper/2303.14361/) (2023)
- [BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies](https://mlsanity.com/paper/2108.09376/) (2021)

## Abstract (arXiv)

We present Accel, a novel semantic video segmentation system that achieves high accuracy at low inference cost by combining the predictions of two network branches: (1) a reference branch that extracts high-detail features on a reference keyframe, and warps these features forward using frame-to-frame optical flow estimates, and (2) an update branch that computes features of adjustable quality on the current frame, performing a temporal update at each video frame. The modularity of the update branch, where feature subnetworks of varying layer depth can be inserted (e.g. ResNet-18 to ResNet-101), enables operation over a new, state-of-the-art accuracy-throughput trade-off spectrum. Over this curve, Accel models achieve both higher accuracy and faster inference times than the closest comparable single-frame segmentation networks. In general, Accel significantly outperforms previous work on efficient semantic video segmentation, correcting warping-related error that compounds on datasets with complex dynamics. Accel is end-to-end trainable and highly modular: the reference network, the optical flow network, and the update network can each be selected independently, depending on application requirements, and then jointly fine-tuned. The result is a robust, general system for fast, high-accuracy semantic segmentation on video.