# One-stage Video Instance Segmentation: From Frame-in Frame-out to Clip-in Clip-out

arXiv: https://arxiv.org/abs/2203.06421 · HTML: https://mlsanity.com/paper/2203.06421/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 31 references that are in the map.
- First posted on arXiv 12 Mar 2022.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation](https://mlsanity.com/paper/2001.00309/) (2020)
- [Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation](https://mlsanity.com/paper/1912.04573/) (2019)
- [Fully Convolutional Instance-aware Semantic Segmentation](https://mlsanity.com/paper/1611.07709/) (2016)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos](https://mlsanity.com/paper/2003.08429/) (2020)
- [SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation](https://mlsanity.com/paper/2007.14772/) (2020)
- [Video Instance Segmentation using Inter-Frame Communication Transformers](https://mlsanity.com/paper/2106.03299/) (2021)
- [SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation](https://mlsanity.com/paper/2103.10284/) (2021)
- [Crossover Learning for Fast Online Video Instance Segmentation](https://mlsanity.com/paper/2104.05970/) (2021)
- [Video Instance Segmentation with a Propose-Reduce Paradigm](https://mlsanity.com/paper/2103.13746/) (2021)
- [MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features](https://mlsanity.com/paper/1712.04837/) (2017)
- [CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation](https://mlsanity.com/paper/2012.03400/) (2020)
- [Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation](https://mlsanity.com/paper/2106.11958/) (2021)
- [Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation](https://mlsanity.com/paper/2104.05606/) (2021)

## Built on by (most cited first, 1 of 1)

- [MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos](https://mlsanity.com/paper/2303.14395/) (2023)

## Abstract (arXiv)

Many video instance segmentation (VIS) methods partition a video sequence into individual frames to detect and segment objects frame by frame. However, such a frame-in frame-out (FiFo) pipeline is ineffective to exploit the temporal information. Based on the fact that adjacent frames in a short clip are highly coherent in content, we propose to extend the one-stage FiFo framework to a clip-in clip-out (CiCo) one, which performs VIS clip by clip. Specifically, we stack FPN features of all frames in a short video clip to build a spatio-temporal feature cube, and replace the 2D conv layers in the prediction heads and the mask branch with 3D conv layers, forming clip-level prediction heads (CPH) and clip-level mask heads (CMH). Then the clip-level masks of an instance can be generated by feeding its box-level predictions from CPH and clip-level features from CMH into a small fully convolutional network. A clip-level segmentation loss is proposed to ensure that the generated instance masks are temporally coherent in the clip. The proposed CiCo strategy is free of inter-frame alignment, and can be easily embedded into existing FiFo based VIS approaches. To validate the generality and effectiveness of our CiCo strategy, we apply it to two representative FiFo methods, Yolact citebolya2019yolact and CondInst citetian2020conditional, resulting in two new one-stage VIS models, namely CiCo-Yolact and CiCo-CondInst, which achieve 37.1/37.3%, 35.2/35.4% and 17.2/18.0% mask AP using the ResNet50 backbone, and 41.8/41.4%, 38.0/38.9% and 18.0/18.2% mask AP using the Swin Transformer tiny backbone on YouTube-VIS 2019, 2021 and OVIS valid sets, respectively, recording new state-of-the-arts. Code and video demos of CiCo can be found at urlhttps://github.com/MinghanLi/CiCo.