# Learning What to Learn for Video Object Segmentation

arXiv: https://arxiv.org/abs/2003.11540 · HTML: https://mlsanity.com/paper/2003.11540/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2020.

## Built on by (most cited first, 30 of 89)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Associating Objects with Transformers for Video Object Segmentation](https://mlsanity.com/paper/2106.02638/) (2021)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [Decoupling Features in Hierarchical Propagation for Video Object Segmentation](https://mlsanity.com/paper/2210.09782/) (2022)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [Transforming Model Prediction for Tracking](https://mlsanity.com/paper/2203.11192/) (2022)
- [Towards Grand Unification of Object Tracking](https://mlsanity.com/paper/2207.07078/) (2022)
- [SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree](https://mlsanity.com/paper/2410.16268/) (2024)
- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [LVOS: A Benchmark for Long-term Video Object Segmentation](https://mlsanity.com/paper/2211.10181/) (2022)
- [Video Instance Segmentation with a Propose-Reduce Paradigm](https://mlsanity.com/paper/2103.13746/) (2021)
- [Hierarchical Memory Matching Network for Video Object Segmentation](https://mlsanity.com/paper/2109.11404/) (2021)
- [A Distractor-Aware Memory for Visual Object Tracking with SAM2](https://mlsanity.com/paper/2411.17576/) (2024)
- [Learning Position and Target Consistency for Memory-based Video Object Segmentation](https://mlsanity.com/paper/2104.04329/) (2021)
- [Joint Inductive and Transductive Learning for Video Object Segmentation](https://mlsanity.com/paper/2108.03679/) (2021)
- [XMem++: Production-level Video Segmentation From Few Annotated Frames](https://mlsanity.com/paper/2307.15958/) (2023)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation](https://mlsanity.com/paper/2404.19326/) (2024)
- [Per-Clip Video Object Segmentation](https://mlsanity.com/paper/2208.01924/) (2022)
- [Deep Reparametrization of Multi-Frame Super-Resolution and Denoising](https://mlsanity.com/paper/2108.08286/) (2021)
- [Robust Visual Tracking by Segmentation](https://mlsanity.com/paper/2203.11191/) (2022)
- [SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization](https://mlsanity.com/paper/2208.10128/) (2022)
- [DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks](https://mlsanity.com/paper/2304.00571/) (2023)
- [UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces](https://mlsanity.com/paper/2312.15715/) (2023)
- [RMem: Restricted Memory Banks Improve Video Object Segmentation](https://mlsanity.com/paper/2406.08476/) (2024)
- [Is First Person Vision Challenging for Object Tracking?](https://mlsanity.com/paper/2108.13665/) (2021)
- [Boosting Video Object Segmentation via Space-time Correspondence Learning](https://mlsanity.com/paper/2304.06211/) (2023)
- [Efficient Track Anything](https://mlsanity.com/paper/2411.18933/) (2024)

## Abstract (arXiv)

Video object segmentation (VOS) is a highly challenging problem, since the target object is only defined during inference with a given first-frame reference mask. The problem of how to capture and utilize this limited target information remains a fundamental research question. We address this by introducing an end-to-end trainable VOS architecture that integrates a differentiable few-shot learning module. This internal learner is designed to predict a powerful parametric model of the target by minimizing a segmentation error in the first frame. We further go beyond standard few-shot learning techniques by learning what the few-shot learner should learn. This allows us to achieve a rich internal representation of the target in the current frame, significantly increasing the segmentation accuracy of our approach. We perform extensive experiments on multiple benchmarks. Our approach sets a new state-of-the-art on the large-scale YouTube-VOS 2018 dataset by achieving an overall score of 81.5, corresponding to a 2.6% relative improvement over the previous best result.