# Deformable VisTR: Spatio temporal deformable attention for video instance segmentation

arXiv: https://arxiv.org/abs/2203.06318 · HTML: https://mlsanity.com/paper/2203.06318/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 21 references that are in the map.
- First posted on arXiv 12 Mar 2022.

## Builds on (most cited first, 20 of 20)

- [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)
- [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 DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (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)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation](https://mlsanity.com/paper/1912.04573/) (2019)
- [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)
- [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)
- [An Empirical Study of Spatial Attention Mechanisms in Deep Networks](https://mlsanity.com/paper/1904.05873/) (2019)
- [CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation](https://mlsanity.com/paper/2012.03400/) (2020)
- [Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation](https://mlsanity.com/paper/2104.05606/) (2021)

## Abstract (arXiv)

Video instance segmentation (VIS) task requires classifying, segmenting, and tracking object instances over all frames in a video clip. Recently, VisTR has been proposed as end-to-end transformer-based VIS framework, while demonstrating state-of-the-art performance. However, VisTR is slow to converge during training, requiring around 1000 GPU hours due to the high computational cost of its transformer attention module. To improve the training efficiency, we propose Deformable VisTR, leveraging spatio-temporal deformable attention module that only attends to a small fixed set of key spatio-temporal sampling points around a reference point. This enables Deformable VisTR to achieve linear computation in the size of spatio-temporal feature maps. Moreover, it can achieve on par performance as the original VisTR with 10× less GPU training hours. We validate the effectiveness of our method on the Youtube-VIS benchmark. Code is available at https://github.com/skrya/DefVIS.