# SA-VIS: Sparse frame Annotations for training Video Instance Segmentation

arXiv: https://arxiv.org/abs/2606.20140 · HTML: https://mlsanity.com/paper/2606.20140/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 43 of its 50 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 30 of 43)

- [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)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [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)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [MOTS: Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/1902.03604/) (2019)
- [Mask2Former for Video Instance Segmentation](https://mlsanity.com/paper/2112.10764/) (2021)
- [Track to Detect and Segment: An Online Multi-Object Tracker](https://mlsanity.com/paper/2103.08808/) (2021)
- [Decoupling Features in Hierarchical Propagation for Video Object Segmentation](https://mlsanity.com/paper/2210.09782/) (2022)
- [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)
- [In Defense of Online Models for Video Instance Segmentation](https://mlsanity.com/paper/2207.10661/) (2022)
- [VITA: Video Instance Segmentation via Object Token Association](https://mlsanity.com/paper/2206.04403/) (2022)
- [MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training](https://mlsanity.com/paper/2208.02245/) (2022)
- [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)
- [DVIS: Decoupled Video Instance Segmentation Framework](https://mlsanity.com/paper/2306.03413/) (2023)
- [Semantic Video Segmentation by Gated Recurrent Flow Propagation](https://mlsanity.com/paper/1612.08871/) (2016)
- [Semantic Video CNNs through Representation Warping](https://mlsanity.com/paper/1708.03088/) (2017)
- [OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation](https://mlsanity.com/paper/2307.09356/) (2023)
- [QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking](https://mlsanity.com/paper/2210.06984/) (2022)
- [Temporally Efficient Vision Transformer for Video Instance Segmentation](https://mlsanity.com/paper/2204.08412/) (2022)
- [CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation](https://mlsanity.com/paper/2012.03400/) (2020)

## Abstract (arXiv)

Recent online video instance segmentation (VIS) methods have achieved impressive results, thus becoming the preferred approach to segment instances in videos. Despite the resurgence of impressive single image models, the online (or semi-online) VIS approaches outperform single-image models (e.g., based on SAM) by using long sequences of densely annotated frames during training. However,such a training setup of VIS is expensive in the sense of compute as well as dense annotations required. In order to solve these major flaws, we argue that the effective modeling of the instances and their evolution in videos do not require densely annotated frames. To that end, we propose a simple and effective module, called Past-frames Feature Propagation (PFP) which aggregates low-dimensional features from the image encoder of multiple frames. This simple low-compute module provides tremendous learning capability in using sparse video frame labels for end-to-end training. Combined with a light-weight frame-specific Instance Queries, our Sparse frame Annotation VIS (SA-VIS) significantly improves performance over its baseline. Most interestingly, our simple design that avoids complexities effectively bridges the gap in accuracy between training on sparsely and densely annotated video sequences. This translates to a mere 0.4% drop in performance of SA-VIS when using annotations for only 1/5 of the images in the dataset. Empirically, SA-VIS shows strong improvements over the baseline on YouTube-VIS 2019/2021/2022 and Occluded VIS (OVIS) and an over 1% improvement in AP on the state-of-the-art in a limited annotations scenario.