# A Semi-Self-Supervised Approach for Dense-Pattern Video Object Segmentation

arXiv: https://arxiv.org/abs/2406.05131 · HTML: https://mlsanity.com/paper/2406.05131/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Searching for Activation Functions](https://mlsanity.com/paper/1710.05941/) (2017)
- [Learning Video Object Segmentation from Static Images](https://mlsanity.com/paper/1612.02646/) (2016)
- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [Self supervised contrastive learning for digital histopathology](https://mlsanity.com/paper/2011.13971/) (2020)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video](https://mlsanity.com/paper/1702.00824/) (2017)
- [Video Object Segmentation Without Temporal Information](https://mlsanity.com/paper/1709.06031/) (2017)
- [RVOS: End-to-End Recurrent Network for Video Object Segmentation](https://mlsanity.com/paper/1903.05612/) (2019)
- [Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2206.12126/) (2022)
- [Learning Fast and Robust Target Models for Video Object Segmentation](https://mlsanity.com/paper/2003.00908/) (2020)
- [SwiftNet: Real-time Video Object Segmentation](https://mlsanity.com/paper/2102.04604/) (2021)
- [Depthwise Convolution is All You Need for Learning Multiple Visual Domains](https://mlsanity.com/paper/1902.00927/) (2019)
- [Make One-Shot Video Object Segmentation Efficient Again](https://mlsanity.com/paper/2012.01866/) (2020)
- [Boosting Video Object Segmentation via Space-time Correspondence Learning](https://mlsanity.com/paper/2304.06211/) (2023)
- [A Spatio-temporal Attention-based Model for Infant Movement Assessment from Videos](https://mlsanity.com/paper/2105.09783/) (2021)
- [AutoCount: Unsupervised Segmentation and Counting of Organs in Field Images](https://mlsanity.com/paper/2007.09178/) (2020)
- [Semi-Self-Supervised Domain Adaptation: Developing Deep Learning Models with Limited Annotated Data for Wheat Head Segmentation](https://mlsanity.com/paper/2405.07157/) (2024)
- [Modified CycleGAN for the synthesization of samples for wheat head segmentation](https://mlsanity.com/paper/2402.15135/) (2024)

## Abstract (arXiv)

Video object segmentation (VOS) -- predicting pixel-level regions for objects within each frame of a video -- is particularly challenging in agricultural scenarios, where videos of crops include hundreds of small, dense, and occluded objects (stems, leaves, flowers, pods) that sway and move unpredictably in the wind. Supervised training is the state-of-the-art for VOS, but it requires large, pixel-accurate, human-annotated videos, which are costly to produce for videos with many densely packed objects in each frame. To address these challenges, we proposed a semi-self-supervised spatiotemporal approach for dense-VOS (DVOS) using a diffusion-based method through multi-task (reconstruction and segmentation) learning. We train the model first with synthetic data that mimics the camera and object motion of real videos and then with pseudo-labeled videos. We evaluate our DVOS method for wheat head segmentation from a diverse set of videos (handheld, drone-captured, different field locations, and different growth stages -- spanning from Boot-stage to Wheat-mature and Harvest-ready). Despite using only a few manually annotated video frames, the proposed approach yielded a high-performing model, achieving a Dice score of 0.79 when tested on a drone-captured external test set. While our method was evaluated on wheat head segmentation, it can be extended to other crops and domains, such as crowd analysis or microscopic image analysis.