mlsanityData to 14 Oct 2026

VideoSAM: A Large Vision Foundation Model for High-Speed Video Segmentation

arXiv 2410.21304 ↗First posted 22 Oct 2024cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

High-speed video (HSV) segmentation is essential for analyzing dynamic physical processes in scientific and industrial applications, such as boiling heat transfer. Existing models like U-Net struggle with generalization and accurately segmenting complex bubble formations. We present VideoSAM, a specialized adaptation of the Segment Anything Model (SAM), fine-tuned on a diverse HSV dataset for phase detection. Through diverse experiments, VideoSAM demonstrates superior performance across four fluid environments -- Water, FC-72, Nitrogen, and Argon -- significantly outperforming U-Net in complex segmentation tasks. In addition to introducing VideoSAM, we contribute an open-source HSV segmentation dataset designed for phase detection, enabling future research in this domain. Our findings underscore VideoSAM's potential to set new standards in robust and accurate HSV segmentation. The code and dataset used in this study are available online at https://github.com/chikap421/videosam.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 61 references that are in the map. First posted on arXiv 22 Oct 2024.

Builds on

24 of 61 references.

References · 24

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  4. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  5. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  6. 2021Domain Generalization: A Surveycited by 764
  7. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  8. 2023Segment Anything Model for Medical Image Analysis: an Experimental Studycited by 291
  9. 2021Associating Objects with Transformers for Video Object Segmentationcited by 226
  10. 2023Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applicationscited by 121
  11. 2023The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shotcited by 83
  12. 2023Adapting Segment Anything Model for Change Detection in HR Remote Sensing Imagescited by 56
12 more
  1. 2024Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applicationscited by 50
  2. 2020Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptationcited by 43
  3. 2019The Domain Shift Problem of Medical Image Segmentation and Vendor-Adaptation by Unet-GANcited by 30
  4. 2020DeepSeg: Deep Neural Network Framework for Automatic Brain Tumor Segmentation using Magnetic Resonance FLAIR Imagescited by 21
  5. 2017ImageJ2: ImageJ for the next generation of scientific image datacited by 14
  6. 2023Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learningcited by 9
  7. 2023Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)cited by 7
  8. 2022Bubble identification from images with machine learning methodscited by 5
  9. 2022Mitigating Both Covariate and Conditional Shift for Domain Generalizationcited by 4
  10. 2024SAM-PD: How Far Can SAM Take Us in Tracking and Segmenting Anything in Videos by Prompt Denoisingcited by 4
  11. 2020Automatic segmentation of CT images for ventral body composition analysiscited by 2
  12. 2024Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Frameworkcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024MSEG-VCUQ: Multimodal SEGmentation with Enhanced Vision Foundation Models, Convolutional Neural Networks, and Uncertainty Quantification for High-Speed Video Phase Detection Datacited by 0